INDEX

Explanations

numerical figures or codes

oai_token-act-pair · gpt-3.5-turbo

numerical identifiers or codes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

istically

-0.84

ufact

-0.81

iful

-0.78

unct

-0.78

inent

-0.78

 unification

-0.72

ises

-0.72

ugal

-0.72

odic

-0.70

endez

-0.70

POSITIVE LOGITS

 cylinders

0.76

 needles

0.72

RNA

0.71

 rods

0.70

é»Ĵ

0.69

æ©Ł

0.69

MHz

0.69

MHz

0.69

RF

0.68

WER

0.67

Activations Density 0.041%

numerical figures or codes

numerical identifiers or codes

No Comments

No Known Activations