INDEX

Explanations

references to sports teams or institutions

oai_token-act-pair · gpt-3.5-turbo

references to specific sports teams and universities

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

terday

-1.02

DonaldTrump

-0.98

imore

-0.95

schild

-0.90

 Seym

-0.80

sembly

-0.79

apons

-0.78

orer

-0.76

colm

-0.75

etsy

-0.74

POSITIVE LOGITS

neys

1.00

Cou

0.96

gars

0.80

ney

0.78

NEY

0.74

 Arabia

0.72

ndra

0.72

 Ducks

0.71

resy

0.70

DVD

0.70

Activations Density 0.045%

references to sports teams or institutions

references to specific sports teams and universities

No Comments

No Known Activations