INDEX

Explanations

phrases related to the United States

oai_token-act-pair · gpt-3.5-turbo

sentences that conclude or summarize information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pus

-0.70

 overboard

-0.59

tom

-0.58

ãĤ©

-0.55

utterstock

-0.55

 vectors

-0.55

 lapt

-0.54

 onboard

-0.54

bably

-0.54

 drill

-0.53

POSITIVE LOGITS

Va

0.91

$.

0.84

0.83

 Geological

0.78

government

0.68

uthor

0.66

 Soccer

0.66

 STATES

0.66

 Nations

0.66

orks

0.65

Activations Density 0.048%

phrases related to the United States

sentences that conclude or summarize information

No Comments

No Known Activations