INDEX

Explanations

the surname "Lim."

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals with the surname "Lim."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dot

-0.75

WS

-0.74

${

-0.68

WS

-0.68

RG

-0.68

enta

-0.66

isters

-0.66

SB

-0.65

azon

-0.65

atz

-0.64

POSITIVE LOGITS

Lim

3.80

Lim

3.09

LIM

1.98

lim

1.84

lim

1.53

 Limits

1.51

 Limit

1.34

 limitations

1.27

Lau

1.23

 limitation

1.21

Activations Density 0.017%

the surname "Lim."

references to specific individuals with the surname "Lim."

No Comments

No Known Activations