INDEX

Explanations

phrases related to indecision or uncertainty

oai_token-act-pair · gpt-3.5-turbo

phrases expressing uncertainty or indecision about actions to take

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

Mur

-0.65

quickShipAvailable

-0.62

 Appears

-0.61

quad

-0.61

dro

-0.59

 Spaces

-0.58

Valid

-0.58

 Nash

-0.57

®

-0.57

Runner

-0.56

POSITIVE LOGITS

 expect

1.16

 prioritize

0.99

eat

0.95

 classify

0.95

buy

0.92

 choose

0.90

 give

0.90

 characterize

0.89

 shove

0.89

igl

0.88

Activations Density 0.059%

phrases related to indecision or uncertainty

phrases expressing uncertainty or indecision about actions to take

No Comments

No Known Activations