INDEX

Explanations

proper nouns related to individuals or locations

oai_token-act-pair · gpt-3.5-turbo

references to specific people or entities, possibly including their names

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

 Volunte

-0.79

Kre

-0.79

TRA

-0.78

Bei

-0.76

Kut

-0.74

AL

-0.74

fri

-0.72

[*

-0.72

coh

-0.72

 --------

-0.71

POSITIVE LOGITS

azon

0.99

ney

0.86

span

0.86

ivia

0.85

iam

0.84

atform

0.84

asper

0.81

raphics

0.81

iph

0.80

yright

0.80

Activations Density 0.366%

proper nouns related to individuals or locations

references to specific people or entities, possibly including their names

No Comments

No Known Activations