INDEX

Explanations

quantitative comparisons or analogies

oai_token-act-pair · gpt-3.5-turbo

phrases that compare the magnitude or significance of different entities or actions

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

erer

-0.69

nesses

-0.67

ETF

-0.67

Beh

-0.66

bender

-0.66

oji

-0.63

................................................................

-0.60

gow

-0.59

Sort

-0.58

ament

-0.58

POSITIVE LOGITS

lihood

0.77

 Shack

0.70

 waking

0.68

FML

0.65

GDP

0.64

agine

0.64

ruciating

0.64

yip

0.63

 Luther

0.62

 equivalent

0.62

Activations Density 0.073%

quantitative comparisons or analogies

phrases that compare the magnitude or significance of different entities or actions

No Comments

No Known Activations