INDEX

Explanations

references to locations, specifically focusing on the state of Nevada

oai_token-act-pair · gpt-3.5-turbo

mentions of the state of Nevada

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

umper

-0.76

fare

-0.75

*/(

-0.74

big

-0.74

cean

-0.74

notation

-0.73

ihad

-0.72

ī

-0.69

eur

-0.69

thood

-0.68

POSITIVE LOGITS

 Nevada

0.94

 Reno

0.79

ites

0.76

ite

0.76

 Coyotes

0.74

Nev

0.74

 crossings

0.73

 Herrera

0.72

 Pradesh

0.72

anan

0.71

Activations Density 0.006%

references to locations, specifically focusing on the state of Nevada

mentions of the state of Nevada

No Comments

No Known Activations