INDEX

Explanations

names related to entertainment or famous individuals

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly those named Norton and Ortiz

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

Negative Logits

kell

-0.79

tered

-0.75

ional

-0.75

ebook

-0.73

¤

-0.72

ulatory

-0.70

ters

-0.70

ulating

-0.69

soDeliveryDate

-0.69

âĸ¬âĸ¬

-0.68

POSITIVE LOGITS

 Norton

1.26

cliffe

0.79

 Howe

0.75

shire

0.73

Downloadha

0.70

sson

0.70

 Vanderbilt

0.68

antage

0.68

 mosqu

0.68

INGTON

0.68

Activations Density 0.015%

names related to entertainment or famous individuals

references to specific individuals, particularly those named Norton and Ortiz

No Known Activations