INDEX

Explanations

terms related to specific topics or concepts, such as drugs, programming languages, and political figures

oai_token-act-pair · gpt-3.5-turbo

specific nouns or proper nouns associated with technology, politics, and culture

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

uminati

-0.73

akable

-0.70

ointed

-0.70

-0.66

£ı

-0.65

ammy

-0.65

chest

-0.62

Ern

-0.61

 Plymouth

-0.60

 Pearce

-0.57

POSITIVE LOGITS

 represents

1.19

isn

1.17

is

1.16

 tends

1.12

 exists

1.11

 lacks

1.11

 attracts

1.10

 itself

1.09

 resembles

1.08

 differs

1.06

Activations Density 0.401%

terms related to specific topics or concepts, such as drugs, programming languages, and political figures

specific nouns or proper nouns associated with technology, politics, and culture

No Comments

No Known Activations