INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

prominent names of individuals and their actions or associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 applause

-0.73

Score

-0.72

chio

-0.64

¿½

-0.64

Pred

-0.61

laugh

-0.61

rating

-0.61

match

-0.60

 Speaking

-0.60

Ô

-0.60

POSITIVE LOGITS

 decided

1.45

 withdrew

1.44

 began

1.43

 became

1.35

 realized

1.34

 realised

1.34

 retreated

1.34

 reverted

1.33

 resumed

1.31

 recons

1.30

Activations Density 0.346%

names of individuals

prominent names of individuals and their actions or associations

No Comments

No Known Activations