INDEX

Explanations

the word "out" or variations of it, such as "outs" and "OUT"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "out."

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

 arsen

-0.90

avorite

-0.74

ajo

-0.68

anguage

-0.68

--------------------------------

-0.65

 subp

-0.65

 downward

-0.65

Îµ

-0.63

 trem

-0.63

ute

-0.63

POSITIVE LOGITS

doors

1.01

lier

0.96

dated

0.94

landish

0.94

door

0.94

fitted

0.92

stretched

0.92

raged

0.89

numbered

0.89

fits

0.87

Activations Density 0.036%

the word "out" or variations of it, such as "outs" and "OUT"

variations of the word "out."

No Comments

No Known Activations