INDEX

Explanations

phrases related to clothing items, specifically shorts

oai_token-act-pair · gpt-3.5-turbo

references to shorts and related clothing items

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

rian

-0.79

Reviewed

-0.75

VERTIS

-0.72

upon

-0.70

————————————————

-0.69

rians

-0.69

Reviewer

-0.67

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.65

Aud

-0.64

APH

-0.64

POSITIVE LOGITS

 shorts

1.57

hirt

1.08

 trousers

1.05

 pants

0.99

leeve

0.96

 jeans

0.95

 socks

0.87

 underwear

0.87

 Shirt

0.86

 sleeves

0.82

Activations Density 0.005%

phrases related to clothing items, specifically shorts

references to shorts and related clothing items

No Comments

No Known Activations