INDEX

Explanations

numerical values and measurements within a text

oai_token-act-pair · gpt-3.5-turbo

punctuation marks or symbols indicating transitions or separations in thoughts or ideas

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utical

-0.65

kees

-0.61

boro

-0.58

 Trog

-0.58

 adolesc

-0.58

ction

-0.56

iton

-0.56

 Creed

-0.56

ennes

-0.55

POSITIVE LOGITS

ÂłÂłÂłÂł

0.90

ÂłÂłÂłÂłÂłÂłÂłÂł

0.89

ÂłÂłÂł

0.87

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.81

Scroll

0.81

SPONSORED

0.78

dain

0.78

thinkable

0.76

sonian

0.73

Yet

0.70

Activations Density 0.455%

numerical values and measurements within a text

punctuation marks or symbols indicating transitions or separations in thoughts or ideas

No Comments

No Known Activations