INDEX

Explanations

references to the name "Diane" with varying activations for different spellings and its association with certain contexts such as sports, crime, and corporate services

oai_token-act-pair · gpt-3.5-turbo

names or references to individuals or characters

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rador

-0.81

-0.80

enance

-0.78

 Carbuncle

-0.76

achusetts

-0.75

enegger

-0.71

ernaut

-0.70

iosity

-0.70

awaru

-0.70

 Seym

-0.69

POSITIVE LOGITS

gas

1.00

jad

0.91

IRO

0.81

ffe

0.81

hyde

0.80

cia

0.78

vil

0.77

venue

0.76

quin

0.75

utenant

0.74

Activations Density 0.044%

references to the name "Diane" with varying activations for different spellings and its association with certain contexts such as sports, crime, and corporate services

names or references to individuals or characters

No Comments

No Known Activations