INDEX

Explanations

programming-related terms or keywords, potentially from code snippets or documentation

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and their associated contextual placements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

achev

-0.77

omorph

-0.71

vised

-0.70

ording

-0.66

arest

-0.65

mination

-0.64

mop

-0.64

vironment

-0.64

est

-0.63

Reviewed

-0.63

POSITIVE LOGITS

 Secondly

1.01

also

0.99

 also

0.99

Another

0.97

Secondly

0.97

 ALSO

0.97

 besides

0.95

 Other

0.95

 other

0.94

 Another

0.91

Activations Density 0.204%

programming-related terms or keywords, potentially from code snippets or documentation

punctuation marks and their associated contextual placements

No Comments

No Known Activations