INDEX

Explanations

mentions of the word "use."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "use" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Beir

-0.68

 Barg

-0.67

 Sandwich

-0.64

Zur

-0.62

bitious

-0.60

 congratulations

-0.59

 passage

-0.59

 hopeful

-0.58

 perfection

-0.58

 Huck

-0.57

POSITIVE LOGITS

fulness

1.36

fully

1.27

FUL

1.16

full

1.14

ful

1.11

cases

1.04

case

0.88

ability

0.87

 Cases

0.87

lessness

0.87

Activations Density 0.070%

mentions of the word "use."

instances of the word "use" in various contexts

No Comments

No Known Activations