INDEX

Explanations

concepts related to uncertainty and questioning knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ReusableCell

-0.62

BorderFactory

-0.58

 OMITBAD

-0.54

zarchiwizowane

-0.54

tanleria

-0.53

 InputDecoration

-0.53

cipar

-0.52

 doInBackground

-0.51

 NavController

-0.51

StoryboardSegue

-0.50

POSITIVE LOGITS

how

4.40

how

3.24

How

2.79

How

2.78

 cómo

2.59

HOW

2.56

 bagaimana

2.44

HOW

2.39

 hvordan

2.36

 what

2.27

Activations Density 1.382%

concepts related to uncertainty and questioning knowledge

No Comments

No Known Activations