INDEX

Explanations

technical terms or jargon related to technology and computing

oai_token-act-pair · gpt-3.5-turbo

phrases related to health crises and warnings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 teasp

-0.69

efficients

-0.62

 exting

-0.61

unctions

-0.60

aturday

-0.59

omnia

-0.59

Lear

-0.58

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.58

÷

-0.58

ü

-0.58

POSITIVE LOGITS

 vapor

0.50

 literal

0.50

 paraph

0.49

 foundational

0.47

 Darth

0.46

 âĢķ

0.46

 grizz

0.46

 Cuban

0.46

 leveraging

0.45

MAC

0.45

Activations Density 1.959%

technical terms or jargon related to technology and computing

phrases related to health crises and warnings

No Comments

No Known Activations