INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

names and references related to specific individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ramer

-0.80

 restroom

-0.71

onym

-0.71

 sober

-0.69

rob

-0.68

unders

-0.62

¥ŀ

-0.62

 denomin

-0.59

oug

-0.59

raught

-0.58

POSITIVE LOGITS

vez

1.39

 Chavez

0.85

 Mush

0.79

 Nieto

0.78

 Perez

0.78

Haf

0.76

 Mubarak

0.75

chev

0.74

vous

0.72

ktop

0.71

Activations Density 0.003%

names of individuals

names and references related to specific individuals

No Comments

No Known Activations