INDEX

Explanations

locations or states in the United States

oai_token-act-pair · gpt-3.5-turbo

references to U.S. states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

å§

-0.77

henko

-0.71

rious

-0.70

uncle

-0.68

bats

-0.66

æĹ

-0.65

ignty

-0.65

aunder

-0.65

kick

-0.65

 sails

-0.64

POSITIVE LOGITS

 Legislature

0.85

 Attorney

0.84

 Springs

0.82

 legislature

0.81

 Police

0.81

 Hills

0.80

 appellate

0.77

 City

0.77

 Municipal

0.75

 Judiciary

0.74

Activations Density 0.399%

locations or states in the United States

references to U.S. states

No Comments

No Known Activations