INDEX

Explanations

single-word terms or phrases

oai_token-act-pair · gpt-3.5-turbo

the usage of the word "term" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ierrez

-0.83

 Guerrero

-0.69

psey

-0.65

 thrott

-0.63

NetMessage

-0.63

 choir

-0.62

Reply

-0.61

xtap

-0.61

isner

-0.61

hs

-0.60

POSITIVE LOGITS

 coined

1.00

icide

0.96

assian

0.91

ifier

0.91

lance

0.82

ename

0.82

aran

0.82

uncle

0.80

marks

0.78

ology

0.78

Activations Density 0.033%

single-word terms or phrases

the usage of the word "term" in various contexts

No Comments

No Known Activations