INDEX

Explanations

phrases indicating gratitude or appreciation

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly exclamation points and question marks

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

mun

-0.76

enf

-0.69

zik

-0.68

oun

-0.63

trap

-0.60

esome

-0.60

ortium

-0.60

quartered

-0.60

encies

-0.59

 repro

-0.59

POSITIVE LOGITS

ãĥ¤

0.87

 Visit

0.75

 Carbuncle

0.72

 Come

0.70

 Wrestling

0.69

 Please

0.68

 Colleg

0.67

%%

0.67

 Voting

0.65

 Subtle

0.64

Activations Density 0.023%

phrases indicating gratitude or appreciation

punctuation marks, particularly exclamation points and question marks

No Comments

No Known Activations