INDEX

Explanations

action verbs related to information processing or technology

oai_token-act-pair · gpt-3.5-turbo

the end of document markers or punctuation indicating conclusion

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

 submar

-0.76

 Frie

-0.68

 Vaugh

-0.68

 Seym

-0.67

 Nare

-0.66

 Beir

-0.65

 Niet

-0.64

emale

-0.62

 Azerb

-0.60

 Maver

-0.60

POSITIVE LOGITS

yon

0.81

ables

0.79

progress

0.75

 guiActiveUnfocused

0.74

ments

0.72

backs

0.69

 html

0.69

able

0.68

eth

0.67

Activations Density 0.104%

action verbs related to information processing or technology

the end of document markers or punctuation indicating conclusion

No Comments

No Known Activations