INDEX

Explanations

mentions of raccoons

oai_token-act-pair · gpt-3.5-turbo

references to racism

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

 Fargo

-0.76

 Ceres

-0.70

 Kush

-0.70

 Hawaiian

-0.69

CPC

-0.66

è£ħ

-0.64

 Dictionary

-0.64

 Ames

-0.64

ITNESS

-0.63

 meaning

-0.63

POSITIVE LOGITS

quet

1.41

coon

1.28

etr

1.18

het

1.15

ework

1.10

quel

1.03

oust

1.02

hett

1.02

kees

1.01

eway

1.01

Activations Density 0.013%

mentions of raccoons

references to racism

No Comments

No Known Activations