INDEX

Explanations

words related to people's names

oai_token-act-pair · gpt-3.5-turbo

instances of the word "ze"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 glim

-0.89

paced

-0.84

ials

-0.83

runner

-0.79

ially

-0.78

runners

-0.76

inarily

-0.74

cutting

-0.74

istrate

-0.73

selling

-0.72

POSITIVE LOGITS

lda

1.30

ppelin

1.21

zinski

1.01

ppel

0.84

ÅĤ

0.84

uble

0.84

itsch

0.82

cki

0.81

zza

0.81

hn

0.79

Activations Density 0.023%

words related to people's names

instances of the word "ze"

No Comments

No Known Activations