INDEX

Explanations

numerical or measurement-related terms

oai_token-act-pair · gpt-3.5-turbo

phrases that approximate quantities or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

oli

-0.68

ves

-0.64

ieu

-0.63

rive

-0.62

alez

-0.62

Express

-0.62

iments

-0.62

oft

-0.61

ousel

-0.61

oa

-0.60

POSITIVE LOGITS

 analogous

0.96

 equivalent

0.83

 WATCHED

0.81

Ĥİ

0.80

 contempor

0.79

Ń·

0.76

 speaking

0.75

 midway

0.75

0.74

Activations Density 0.033%

numerical or measurement-related terms

phrases that approximate quantities or measurements

No Comments

No Known Activations