INDEX

Explanations

terms related to laws or regulations

oai_token-act-pair · gpt-3.5-turbo

language related to negative or critical evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Schumer

-0.87

ModLoader

-0.80

 Dickinson

-0.80

 Shutterstock

-0.80

 Cotton

-0.78

 Gillespie

-0.76

 Harvey

-0.75

 Maher

-0.75

 Benny

-0.74

 Brus

-0.73

POSITIVE LOGITS

sounding

1.23

looking

1.20

minded

1.15

advertising

1.10

bodied

1.03

enough

1.01

advertisement

1.01

themed

1.01

based

1.00

earth

1.00

Activations Density 0.133%

terms related to laws or regulations

language related to negative or critical evaluations

No Comments

No Known Activations