INDEX

Explanations

words related to geographical locations or people's names

oai_token-act-pair · gpt-3.5-turbo

references to the name "Anar" and its derivatives

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

accompan

-0.94

directory

-0.79

tesy

-0.78

ilst

-0.75

illian

-0.74

Orderable

-0.73

iery

-0.72

©¶æ

-0.71

atform

-0.70

Haunted

-0.69

POSITIVE LOGITS

ov

0.88

 Ball

0.86

roth

0.81

Qu

0.76

que

0.76

 Sequ

0.75

val

0.73

quet

0.73

ãĥĪ

0.72

Äĩ

0.72

Activations Density 0.368%

words related to geographical locations or people's names

references to the name "Anar" and its derivatives

No Comments

No Known Activations