INDEX

Explanations

questions related to the type or category of something

oai_token-act-pair · gpt-3.5-turbo

phrases that inquire about types or categories of things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ĸļ

-0.65

 Beir

-0.62

arning

-0.62

YR

-0.60

ARY

-0.60

ENTION

-0.57

VEL

-0.56

 Eisen

-0.56

alus

-0.56

athed

-0.55

POSITIVE LOGITS

of

0.81

iles

0.78

 tastes

0.73

 havoc

0.73

 interests

0.68

nes

0.67

 Flavoring

0.67

croft

0.63

of

0.63

 thereof

0.62

Activations Density 0.036%

questions related to the type or category of something

phrases that inquire about types or categories of things

No Comments

No Known Activations