INDEX

Explanations

mentions of types of footwear, especially shoes

oai_token-act-pair · gpt-3.5-turbo

references to shoes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

umbn

-0.80

enance

-0.73

yrinth

-0.70

 horm

-0.69

SHIP

-0.67

iov

-0.65

ancial

-0.65

ENTS

-0.65

REDACTED

-0.64

itative

-0.63

POSITIVE LOGITS

toe

1.11

 shoes

1.04

horn

0.99

 footwear

0.99

 worn

0.95

 heel

0.94

prints

0.91

pins

0.91

pees

0.91

wear

0.90

Activations Density 0.044%

mentions of types of footwear, especially shoes

references to shoes

No Comments

No Known Activations