INDEX

Explanations

structural elements and identifiers in data or documents

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

بوابة

-0.77

findpost

-0.72

 Савезне

-0.72

:]:

-0.63

Hilsen

-0.59

GEBURTS

-0.57

ArgumentParser

-0.56

ագրություններ

-0.55

dolu

-0.54

học

-0.53

POSITIVE LOGITS

 porc

0.55

 ddelweddau

0.55

кну

0.51

 TestBed

0.51

 ujednoznacz

0.49

Bioaccumulative

0.49

Initializable

0.48

Externí

0.48

Rüyada

0.47

TRAILING

0.46

Activations Density 1.467%

structural elements and identifiers in data or documents

No Comments

No Known Activations