INDEX

Explanations

programming-related terms and commands

oai_token-act-pair · gpt-3.5-turbo

empty or non-informative content

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

?ãĢį

-0.66

ILY

-0.66

 ÂŃ

-0.64

dam

-0.64

 rash

-0.63

SPONSORED

-0.62

 biod

-0.61

 sluggish

-0.59

––

-0.57

vig

-0.57

POSITIVE LOGITS

resa

0.87

cloneembedreportprint

0.84

 Conclusion

0.79

aeda

0.78

odore

0.78

notations

0.78

ibliography

0.77

anmar

0.77

iple

0.77

uyomi

0.76

Activations Density 0.375%

programming-related terms and commands

empty or non-informative content

No Comments

No Known Activations

programming-related terms and commands

empty or non-informative content

No Comments

No Known Activations