INDEX

Explanations

proper nouns, specifically names of individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or names in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ALLY

-0.77

NetMessage

-0.73

opausal

-0.72

eers

-0.71

netflix

-0.70

 Disneyland

-0.68

 Kinnikuman

-0.64

naissance

-0.64

ĺħ

-0.63

ISE

-0.62

POSITIVE LOGITS

atche

1.07

rite

0.97

mus

0.93

ani

0.87

ans

0.86

aku

0.86

inx

0.85

aji

0.85

onso

0.85

arah

0.83

Activations Density 0.030%

proper nouns, specifically names of individuals

mentions of specific individuals or names in the text

No Comments

No Known Activations