INDEX

Explanations

relations between different entities within a system

oai_token-act-pair · gpt-3.5-turbo

instances of the word "that."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 guessing

-0.67

LY

-0.65

ZI

-0.63

heard

-0.62

done

-0.62

roy

-0.62

 Charg

-0.61

 pric

-0.61

WAY

-0.58

 Landing

-0.57

POSITIVE LOGITS

 governs

1.35

 encompasses

1.30

 extends

1.29

 perv

1.26

 spans

1.24

 arises

1.24

 dominates

1.24

 culmin

1.23

 persists

1.23

 accompanies

1.23

Activations Density 0.250%

relations between different entities within a system

instances of the word "that."

No Comments

No Known Activations