INDEX

Explanations

statistics or research findings

oai_token-act-pair · gpt-3.5-turbo

instances of the word "found" indicating reported research results or discoveries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

arta

-0.66

awar

-0.66

EStreamFrame

-0.65

 Pastebin

-0.62

icio

-0.59

clock

-0.59

fen

-0.59

press

-0.59

quer

-0.58

bec

-0.58

POSITIVE LOGITS

 conclusive

0.84

 evidence

0.84

ered

0.80

 traces

0.79

 widespread

0.79

 fault

0.74

 significant

0.74

 similarities

0.71

 nothing

0.70

 plenty

0.70

Activations Density 0.059%

statistics or research findings

instances of the word "found" indicating reported research results or discoveries

No Comments

No Known Activations