INDEX

Explanations

mentions of the location "Charlottesville."

oai_token-act-pair · gpt-3.5-turbo

mentions of "Charlottesville."

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

reason

-0.77

VIS

-0.76

lev

-0.75

ever

-0.74

berman

-0.73

served

-0.71

pring

-0.71

vana

-0.70

integer

-0.69

aft

-0.69

POSITIVE LOGITS

ottesville

1.14

halla

0.91

sburg

0.87

 Charlottesville

0.81

querque

0.76

quished

0.71

 Heights

0.68

 racists

0.67

enburg

0.67

 Evening

0.66

Activations Density 0.005%

mentions of the location "Charlottesville."

mentions of "Charlottesville."

No Comments

No Known Activations