INDEX

Explanations

queries or questions within a text

oai_token-act-pair · gpt-3.5-turbo

questions related to various topics

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

 McMaster

-0.71

isconsin

-0.70

 inactive

-0.62

orthern

-0.62

lessly

-0.61

monton

-0.60

hene

-0.60

 extrad

-0.60

ben

-0.60

 unpublished

-0.60

POSITIVE LOGITS

Answer

1.20

YES

0.99

Yes

0.98

ccording

0.89

RH

0.89

Well

0.87

?????-?????-

0.86

Yeah

0.84

Brow

0.84

Trivia

0.84

Activations Density 0.119%

queries or questions within a text

questions related to various topics

No Comments

No Known Activations