INDEX

Explanations

phrases related to significant or impactful concepts or events

oai_token-act-pair · gpt-3.5-turbo

key terms and phrases related to television shows, movies, and entertainment events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 surpr

-0.81

stocks

-0.63

wcs

-0.59

bi

-0.58

 captcha

-0.57

clock

-0.55

 barg

-0.55

changes

-0.55

bats

-0.55

erial

-0.54

POSITIVE LOGITS

 Productions

0.76

 Labs

0.75

Ltd

0.71

 Studios

0.68

 Foundation

0.66

 Enterprises

0.65

 Interactive

0.64

anooga

0.64

 Website

0.64

's

0.63

Activations Density 0.462%

phrases related to significant or impactful concepts or events

key terms and phrases related to television shows, movies, and entertainment events

No Comments

No Known Activations