INDEX

Explanations

words related to legal actions or consequences like "impeached," "beached," or "attached."

oai_token-act-pair · gpt-3.5-turbo

words related to political impeachment and legal proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 punches

-0.67

 digit

-0.63

 patron

-0.62

 instruments

-0.62

PAT

-0.61

Labor

-0.60

Pat

-0.59

ONES

-0.58

opp

-0.58

 gender

-0.57

POSITIVE LOGITS

ached

4.49

aching

2.52

aches

2.18

achment

2.00

achable

1.99

ACH

1.63

ach

1.62

acher

1.50

achers

1.47

ache

1.35

Activations Density 0.014%

words related to legal actions or consequences like "impeached," "beached," or "attached."

words related to political impeachment and legal proceedings

No Comments

No Known Activations