INDEX

Explanations

quantitative phrases indicating a small percentage or number of something

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a small quantity or percentage

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

 Aging

-0.65

ilon

-0.64

wrapper

-0.64

 Assessment

-0.62

ACTION

-0.62

DNA

-0.59

ansion

-0.59

 Jacket

-0.57

 Bust

-0.57

AFTA

-0.56

POSITIVE LOGITS

est

1.13

er

1.04

 exceptions

0.98

eenth

0.92

ever

0.90

een

0.88

 mortals

0.87

 surprises

0.87

 clues

0.86

 specifics

0.86

Activations Density 0.041%

quantitative phrases indicating a small percentage or number of something

phrases that indicate a small quantity or percentage

No Comments

No Known Activations