INDEX

Explanations

dates and numerical figures expressed in a specific format

oai_token-act-pair · gpt-3.5-turbo

numerical data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 fateful

-0.72

 nomine

-0.69

 shopping

-0.68

 sidew

-0.68

 corrid

-0.67

 bunny

-0.67

 thous

-0.66

 tremend

-0.65

agna

-0.63

 canned

-0.63

POSITIVE LOGITS

0.94

MQ

0.93

0.92

0.91

0.90

0.89

0.88

Activations Density 0.144%

dates and numerical figures expressed in a specific format

numerical data and statistics

No Comments

No Known Activations