INDEX

Explanations

verbs related to actions or discoveries

oai_token-act-pair · gpt-3.5-turbo

verbs related to actions of discovery, accomplishment, and intervention

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

Not in Any Lists

No Comments

Negative Logits

pmwiki

-0.86

ItemTracker

-0.86

Reviewer

-0.73

lihood

-0.72

 caveat

-0.70

wikipedia

-0.69

 knack

-0.62

 sqor

-0.60

 towel

-0.57

 Bleach

-0.56

POSITIVE LOGITS

cliffe

0.67

enance

0.66

tackle

0.66

ISE

0.65

inton

0.65

him

0.63

eline

0.63

uate

0.62

agine

0.61

guide

0.59

Activations Density 0.517%

verbs related to actions or discoveries

verbs related to actions of discovery, accomplishment, and intervention

No Comments

No Known Activations