INDEX

Explanations

terms related to big entities or corporations

oai_token-act-pair · gpt-3.5-turbo

entities and terms related to commerce, social networks, and groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Ô

-0.71

iHUD

-0.68

obyl

-0.67

estern

-0.64

 Assignment

-0.63

bernatorial

-0.63

endas

-0.63

cipled

-0.58

################

-0.58

emia

-0.58

POSITIVE LOGITS

's

1.00

maker

0.75

 itself

0.75

ÃŃs

0.66

hemoth

0.64

runner

0.62

 headquartered

0.59

apo

0.59

 titan

0.58

\'

0.58

Activations Density 0.285%

terms related to big entities or corporations

entities and terms related to commerce, social networks, and groups

No Comments

No Known Activations