INDEX

Explanations

regulations or prohibitions related to specific actions or groups

oai_token-act-pair · gpt-3.5-turbo

references to prohibitions and bans

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

patch

-0.77

hematic

-0.70

 partName

-0.70

 mirac

-0.67

cule

-0.66

figure

-0.66

framework

-0.65

stack

-0.64

ustration

-0.64

Lind

-0.64

POSITIVE LOGITS

 exceptions

0.92

 permitted

0.89

 permissible

0.84

 exemptions

0.83

arate

0.82

 allowable

0.81

 minors

0.81

 prohibited

0.80

 unrestricted

0.76

exempt

0.74

Activations Density 0.705%

regulations or prohibitions related to specific actions or groups

references to prohibitions and bans

No Comments

No Known Activations