INDEX

Explanations

statements indicating disbelief or skepticism

oai_token-act-pair · gpt-3.5-turbo

expressions of strong opinions or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

catentry

-1.02

cffffcc

-0.72

entimes

-0.71

ODUCT

-0.70

etermined

-0.68

Physical

-0.68

Initially

-0.64

lication

-0.63

ÂłÂłÂłÂł

-0.63

TEXT

-0.63

POSITIVE LOGITS

 kidding

0.96

ya

0.92

;)

0.80

 idiots

0.79

 bullshit

0.78

 nerds

0.77

 Stupid

0.76

 whining

0.76

 fools

0.75

ain

0.74

Activations Density 1.543%

statements indicating disbelief or skepticism

expressions of strong opinions or sentiments

No Comments

No Known Activations