INDEX

Explanations

phrases indicating addition or inclusion

oai_token-act-pair · gpt-3.5-turbo

references to actions or contributions made to a larger context or situation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CHAT

-0.78

glers

-0.75

ITCH

-0.68

 mailed

-0.67

rowth

-0.60

Released

-0.57

 Dane

-0.56

 Reporter

-0.56

EEP

-0.56

âĢ²

-0.56

POSITIVE LOGITS

 compensate

0.78

folio

0.66

 complement

0.66

othy

0.65

balanced

0.64

 bolster

0.64

 Balance

0.64

ventory

0.63

 counteract

0.63

Ore

0.62

Activations Density 0.110%

phrases indicating addition or inclusion

references to actions or contributions made to a larger context or situation

No Comments

No Known Activations