INDEX

Explanations

mathematical expressions and technical terms related to data processing

oai_token-act-pair · gpt-3.5-turbo

technical terms and symbols related to data structures and algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hap

-0.76

google

-0.71

uyomi

-0.63

 Hugo

-0.63

 GOODMAN

-0.62

apeshifter

-0.62

 Gorge

-0.61

¥µ

-0.60

angel

-0.60

sus

-0.59

POSITIVE LOGITS

1.20

(-

1.16

(_

1.09

('

1.01

0.98

())

0.98

(\

0.96

(&

0.93

([

0.92

("

0.92

Activations Density 0.152%

mathematical expressions and technical terms related to data processing

technical terms and symbols related to data structures and algorithms

No Comments

No Known Activations