INDEX

Explanations

rules, permissions, or regulations mentioned in text

oai_token-act-pair · gpt-3.5-turbo

terms related to permissions and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

tal

-0.81

hs

-0.80

hack

-0.79

war

-0.76

brand

-0.75

 Corinthians

-0.73

chest

-0.71

along

-0.70

gor

-0.69

chenko

-0.69

POSITIVE LOGITS

 permitted

1.23

Reviewer

1.07

ĸļ

0.93

 permitting

0.92

 allowed

0.90

 permissible

0.88

 guiActiveUn

0.87

 authorised

0.82

 authorized

0.80

 guiActive

0.79

Activations Density 0.007%

rules, permissions, or regulations mentioned in text

terms related to permissions and regulations

No Comments

No Known Activations