INDEX

Explanations

phrases related to being well-matched or appropriate for a particular purpose or situation

oai_token-act-pair · gpt-3.5-turbo

terms related to suitability or appropriateness for a given context or group

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 VIDEOS

-0.78

ãĥ£

-0.65

 aborted

-0.64

agic

-0.63

dash

-0.62

inth

-0.62

NCT

-0.61

tery

-0.60

bish

-0.59

ä¼

-0.59

POSITIVE LOGITS

 suited

0.92

xual

0.86

 fitt

0.76

folios

0.74

fit

0.73

ratulations

0.71

 tailor

0.69

estro

0.69

 compliment

0.66

glers

0.65

Activations Density 0.019%

phrases related to being well-matched or appropriate for a particular purpose or situation

terms related to suitability or appropriateness for a given context or group

No Known Activations