INDEX

Explanations

associations with themes related to art or artistic endeavors

oai_token-act-pair · gpt-3.5-turbo

references to art or artistic concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

EStream

-0.72

 Benghazi

-0.69

 Cyprus

-0.66

 Philly

-0.63

 Herm

-0.63

 snowy

-0.60

 nickel

-0.59

 dime

-0.59

 Virtue

-0.59

 pepper

-0.59

POSITIVE LOGITS

ifact

1.21

art

1.12

illery

1.08

ificial

1.07

isans

1.06

esian

1.00

icles

0.99

oon

0.98

emis

0.96

istry

0.96

Activations Density 0.009%

associations with themes related to art or artistic endeavors

references to art or artistic concepts

No Comments

No Known Activations