INDEX

Explanations

the word "automatic" along with variations of it in the text

oai_token-act-pair · gpt-3.5-turbo

words related to automation and automatic processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ĸļ

-1.06

ippi

-0.89

gdala

-0.87

borough

-0.85

yip

-0.83

nan

-0.73

boro

-0.73

mos

-0.72

akov

-0.71

rast

-0.71

POSITIVE LOGITS

ized

0.94

 transmission

0.94

 sprink

0.92

ised

0.88

immune

0.86

izable

0.86

 renewal

0.86

upd

0.85

 updating

0.84

isable

0.80

Activations Density 0.038%

the word "automatic" along with variations of it in the text

words related to automation and automatic processes

No Comments

No Known Activations