INDEX

Explanations

text related to bans or prohibitions on certain actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

references to bans or prohibitions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Dig

-0.71

dden

-0.70

esta

-0.67

cture

-0.66

 enterprise

-0.66

 Square

-0.65

×Ķ

-0.65

Function

-0.65

 formula

-0.63

 impression

-0.62

POSITIVE LOGITS

 bans

3.99

 Bans

2.60

 banning

2.06

ban

1.87

 prohibitions

1.87

 banned

1.84

Ban

1.55

ban

1.37

 punishments

1.33

 outlaw

1.31

Activations Density 0.016%

text related to bans or prohibitions on certain actions or behaviors

references to bans or prohibitions

No Comments

No Known Activations