INDEX

Explanations

references to highly valuable or significant items or concepts

oai_token-act-pair · gpt-3.5-turbo

phrases or concepts related to significant or transformative moments

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

 phased

-0.62

 Jian

-0.60

ĪĴ

-0.59

yi

-0.56

chlor

-0.55

 Chel

-0.55

Sed

-0.54

enza

-0.54

Enough

-0.53

 Editors

-0.53

POSITIVE LOGITS

oots

0.74

omes

0.71

imes

0.71

acters

0.68

alog

0.68

angers

0.67

ivities

0.67

usters

0.67

OME

0.66

akings

0.66

Activations Density 0.210%

references to highly valuable or significant items or concepts

phrases or concepts related to significant or transformative moments

No Comments

No Known Activations