INDEX

Explanations

phrases indicating intentional actions taken for a specific purpose or result

oai_token-act-pair · gpt-3.5-turbo

the word "just" 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ership

-0.62

lore

-0.60

eers

-0.60

aging

-0.59

apolis

-0.58

azor

-0.57

essor

-0.56

 contention

-0.56

pora

-0.55

 Archdemon

-0.55

POSITIVE LOGITS

ifications

1.12

ifiable

1.05

itia

0.89

if

0.85

 desserts

0.82

IFIED

0.81

ices

0.79

inian

0.78

IFIC

0.76

FY

0.75

Activations Density 0.071%

phrases indicating intentional actions taken for a specific purpose or result

the word "just" in various contexts

No Comments

No Known Activations