INDEX

Explanations

names of political or public figures

oai_token-act-pair · gpt-3.5-turbo

isolated single letters or characters, particularly at the beginning of words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

artifacts

-0.68

hett

-0.63

CoC

-0.63

ashtra

-0.62

ELF

-0.61

channelAvailability

-0.61

TextColor

-0.59

lasses

-0.58

Measure

-0.58

AUD

-0.58

POSITIVE LOGITS

uala

0.88

 Alvarez

0.85

 Camer

0.80

icz

0.75

wu

0.74

uma

0.72

oglu

0.70

ulum

0.70

 Philippe

0.68

Tec

0.65

Activations Density 0.220%

names of political or public figures

isolated single letters or characters, particularly at the beginning of words

No Comments

No Known Activations