INDEX

Explanations

phrases starting with "In"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "In" used to introduce statements or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 spoil

-0.72

 unemploy

-0.68

 lett

-0.65

reon

-0.65

:/

-0.63

 looms

-0.63

 unlocks

-0.62

 creeps

-0.61

 babe

-0.60

 combatants

-0.60

POSITIVE LOGITS

cluding

1.29

 addition

1.28

ventory

1.24

 contrast

1.16

 spite

1.15

iti

1.11

jured

1.11

wards

1.09

 lieu

1.09

flation

1.09

Activations Density 0.145%

phrases starting with "In"

instances of the word "In" used to introduce statements or reports

No Comments

No Known Activations