INDEX

Explanations

words or phrases related to being banned or barred from certain actions or places

oai_token-act-pair · gpt-3.5-turbo

terms related to restrictions or prohibitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

worn

-0.81

Engineers

-0.73

imon

-0.68

cule

-0.66

hidden

-0.66

framework

-0.65

 disappoint

-0.65

dimension

-0.65

ensional

-0.63

});

-0.63

POSITIVE LOGITS

 indefinitely

0.88

 altogether

0.85

atever

0.82

 interstate

0.76

 premises

0.72

 activities

0.71

 accessing

0.70

 participating

0.70

 flights

0.69

 offending

0.68

Activations Density 0.477%

words or phrases related to being banned or barred from certain actions or places

terms related to restrictions or prohibitions

No Comments

No Known Activations