INDEX

Explanations

mentions of software versions or updates

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cloudflare

-0.52

 defaultstate

-0.50

SBATCH

-0.45

mes

-0.45

 date

-0.44

ื่อง

-0.43

orcid

-0.43

Mes

-0.40

 شهادت

-0.38

ోగ

-0.38

POSITIVE LOGITS

 Paglinawan

0.79

 itſelf

0.75

RegressionTest

0.71

 poffe

0.69

 Wikimedijinoj

0.69

amaño

0.66

 myſelf

0.66

 uſed

0.65

ImageContext

0.63

 Noyes

0.63

Activations Density 0.587%

mentions of software versions or updates

No Comments

No Known Activations