INDEX

Explanations

detailed descriptions or explanations

oai_token-act-pair · gpt-3.5-turbo

statements about withholding information or not providing details

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ourses

-0.62

hiba

-0.62

 reperto

-0.61

 manag

-0.59

-0.58

fif

-0.57

pes

-0.57

footed

-0.56

few

-0.55

thirds

-0.54

POSITIVE LOGITS

 anymore

1.22

 myself

0.94

 specifics

0.94

nor

0.90

 anything

0.85

 necessarily

0.83

ANY

0.82

 anybody

0.79

 spoilers

0.79

any

0.78

Activations Density 0.399%

detailed descriptions or explanations

statements about withholding information or not providing details

No Comments

No Known Activations