INDEX

Explanations

measurements or numerical quantities, such as lengths, distances, percentages, and times

oai_token-act-pair · gpt-3.5-turbo

quantities and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulture

-0.60

vice

-0.59

 crowds

-0.59

 caveat

-0.57

 leadership

-0.55

rities

-0.55

 congratulations

-0.55

 attitude

-0.55

Else

-0.55

deals

-0.54

POSITIVE LOGITS

 inches

0.95

inches

0.92

years

0.89

 dimensional

0.87

teenth

0.86

een

0.83

cm

0.82

awed

0.81

dimensional

0.80

uously

0.80

Activations Density 0.199%

measurements or numerical quantities, such as lengths, distances, percentages, and times

quantities and measurements

No Comments

No Known Activations