INDEX

Explanations

code-related terms and syntax

oai_token-act-pair · gpt-3.5-turbo

structured data and coding syntax elements

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

\\\\\\\\

-0.63

NESS

-0.62

rawler

-0.60

 itself

-0.59

EH

-0.59

enance

-0.58

 interference

-0.58

 guts

-0.58

ONSORED

-0.58

 arrang

-0.57

POSITIVE LOGITS

txt

0.87

 Included

0.85

were

0.83

 abound

0.78

 Held

0.78

poons

0.78

ettings

0.78

etc

0.76

 Including

0.76

 Tags

0.74

Activations Density 0.463%

code-related terms and syntax

structured data and coding syntax elements

No Comments

No Known Activations