INDEX

Explanations

proper nouns related to specific people or places

oai_token-act-pair · gpt-3.5-turbo

names and terms associated with specific individuals or entities

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

lished

-0.79

oÄŁ

-0.75

nels

-0.74

culosis

-0.73

ulating

-0.73

insula

-0.72

ulation

-0.72

ulated

-0.71

sylvania

-0.70

structed

-0.70

POSITIVE LOGITS

 Luthor

0.96

oyd

0.90

uggage

0.85

ibrary

0.85

yrics

0.80

adders

0.73

ongevity

0.72

 Lamp

0.72

ocate

0.71

 Messi

0.71

Activations Density 0.094%

proper nouns related to specific people or places

names and terms associated with specific individuals or entities

No Comments

No Known Activations