INDEX

Explanations

references to the city of San Francisco

oai_token-act-pair · gpt-3.5-turbo

mentions of San Francisco (SF)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lain

-0.84

stall

-0.83

taker

-0.73

pins

-0.71

berus

-0.71

hift

-0.69

abase

-0.69

pin

-0.68

 Kant

-0.67

iasis

-0.67

POSITIVE LOGITS

PD

1.00

 Chronicle

0.98

WA

0.97

SF

0.94

ML

0.92

ORE

0.91

DC

0.91

ORTS

0.90

WD

0.89

DF

0.88

Activations Density 0.010%

references to the city of San Francisco

mentions of San Francisco (SF)

No Comments

No Known Activations