INDEX

Explanations

proper nouns related to individuals, particularly names

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals and brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ences

-0.82

ential

-0.81

enced

-0.68

--------------------------------------------------------

-0.67

LINE

-0.64

tein

-0.63

swick

-0.63

body

-0.63

PATH

-0.63

ilee

-0.62

POSITIVE LOGITS

 Mats

1.26

ushima

1.09

ura

1.00

 mats

0.98

wana

0.79

 misunder

0.78

awan

0.77

uchin

0.76

aido

0.75

 Kats

0.73

Activations Density 0.009%

proper nouns related to individuals, particularly names

references to specific individuals and brands

No Comments

No Known Activations