INDEX

Explanations

questions and interrogative phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Existenz

-0.56

 kysy

-0.51

 ujednoznacz

-0.51

 Riproduzione

-0.48

 ayudarte

-0.46

 queima

-0.46

 Roskov

-0.45

RTEE

-0.43

 wiesz

-0.43

 Partagez

-0.42

POSITIVE LOGITS

WidgetItem

0.71

riwal

0.71

 GeoNames

0.69

rungsseite

0.66

SourceChecksum

0.63

ătate

0.63

caloosa

0.63

 grpc

0.61

帖最后由

0.61

 Mors

0.60

Activations Density 0.210%

questions and interrogative phrases

No Comments

No Known Activations