INDEX

Explanations

phrases that convey understanding and familiarity in a given context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Obrázky

-0.64

djangoproject

-0.58

bcryptjs

-0.57

gane

-0.56

 springfox

-0.55

っこう

-0.54

 uuidv

-0.52

Itoa

-0.52

WebElementEntity

-0.52

lobo

-0.52

POSITIVE LOGITS

 know

2.31

 knows

2.30

 knowledge

2.26

know

2.20

Know

2.17

 Know

2.08

 knowing

2.01

 knew

1.95

knowledge

1.94

knows

1.91

Activations Density 0.535%

phrases that convey understanding and familiarity in a given context

No Comments

No Known Activations