INDEX

Explanations

mentions of or references to death

oai_token-act-pair · gpt-3.5-turbo

references to death

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Cola

-0.87

umar

-0.80

Avg

-0.75

ECA

-0.74

kef

-0.74

OPER

-0.73

CN

-0.71

ĸļ

-0.70

æ©Ł

-0.70

EEK

-0.70

POSITIVE LOGITS

 toll

0.96

bed

0.89

blow

0.89

stroke

0.87

guard

0.80

adder

0.80

match

0.77

 psychiat

0.76

 Toll

0.76

 penalty

0.76

Activations Density 0.031%

mentions of or references to death

references to death

No Comments

No Known Activations