INDEX

Explanations

phrases related to numerical values and rankings

oai_token-act-pair · gpt-3.5-turbo

negative sentiments towards decisions or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Dickinson

-0.89

 Scrib

-0.89

 Burr

-0.88

 Yelp

-0.87

 Lovecraft

-0.86

ulhu

-0.86

 Boone

-0.83

 Vaughn

-0.78

 Cobb

-0.78

 Chandler

-0.76

POSITIVE LOGITS

based

1.11

linked

1.11

backed

1.10

government

1.05

organ

1.04

bour

1.03

shaped

1.03

turned

1.03

Britain

1.02

national

1.00

Activations Density 0.270%

phrases related to numerical values and rankings

negative sentiments towards decisions or actions

No Comments

No Known Activations