INDEX

Explanations

words related to statements or quotations

oai_token-act-pair · gpt-3.5-turbo

phrases that express opinions or describe conditions about a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

luaj

-0.92

edIn

-0.71

Versions

-0.66

aired

-0.65

bies

-0.63

arthed

-0.62

lat

-0.62

%%

-0.61

andise

-0.61

resp

-0.61

POSITIVE LOGITS

 definitely

1.08

 gonna

0.97

 gotta

0.94

 bitters

0.94

 basically

0.90

 certainly

0.89

 unbelievable

0.88

 frustrating

0.84

 honestly

0.84

 obviously

0.83

Activations Density 0.281%

words related to statements or quotations

phrases that express opinions or describe conditions about a subject

No Comments

No Known Activations