INDEX

Explanations

phrases or terms related to segments or sections within a context

oai_token-act-pair · gpt-3.5-turbo

references to various segments in a content or media discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

CHA

-0.72

 brink

-0.65

 opio

-0.64

cia

-0.63

 realism

-0.62

 drafting

-0.60

 IMAGES

-0.60

 mother

-0.60

 fists

-0.58

kens

-0.57

POSITIVE LOGITS

ation

0.98

arily

0.87

ially

0.87

ated

0.86

eston

0.84

 segments

0.81

ials

0.81

regate

0.80

ational

0.80

igr

0.80

Activations Density 0.010%

phrases or terms related to segments or sections within a context

references to various segments in a content or media discussion

No Comments

No Known Activations