INDEX

Explanations

sections indicating high activation values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ReusableCell

-0.73

urlpatterns

-0.66

DllImport

-0.64

 ujednoznacz

-0.63

cmath

-0.62

setHorizontal

-0.59

LEncoder

-0.59

DrawerLayout

-0.57

complexContent

-0.57

 GlobalKey

-0.56

POSITIVE LOGITS

 abstrait

0.68

laß

0.56

 scolaires

0.51

 juridiques

0.51

 puissiez

0.50

 pédagogique

0.48

ríamos

0.48

 clinique

0.48

ستاگرام

0.48

 mourir

0.48

Activations Density 0.028%

sections indicating high activation values

No Comments

No Known Activations