INDEX

Explanations

words related to specific sections or parts of a document or text

oai_token-act-pair · gpt-3.5-turbo

references to specific sections or divisions within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

cia

-0.73

 opio

-0.69

 Bridges

-0.66

risome

-0.62

ampa

-0.59

agascar

-0.59

riel

-0.59

 realism

-0.58

 Fighters

-0.58

ARA

-0.57

POSITIVE LOGITS

al

0.92

ions

0.87

ials

0.82

bare

0.81

alist

0.81

meal

0.80

ĸļ

0.79

als

0.79

ality

0.78

arians

0.78

Activations Density 0.029%

words related to specific sections or parts of a document or text

references to specific sections or divisions within a document

No Comments

No Known Activations