INDEX

Explanations

mentions of the name "Les"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Les" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ICE

-0.75

DERR

-0.71

ãĥĥãĥĪ

-0.69

ĻĤ

-0.69

ãĥ¼ãĥĨãĤ£

-0.69

ACTED

-0.68

OWS

-0.66

ANI

-0.65

¥ŀ

-0.64

oted

-0.64

POSITIVE LOGITS

bians

1.12

bian

0.99

ukemia

0.84

wana

0.83

nar

0.81

earchers

0.80

alog

0.80

lie

0.79

Les

0.78

ongh

0.78

Activations Density 0.008%

mentions of the name "Les"

mentions of the word "Les" in various contexts

No Comments

No Known Activations