INDEX

Explanations

references to modules in a programming or documentation context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

StructEnd

-0.69

Jeografia

-0.66

kloped

-0.66

Хьажоргаш

-0.63

ArrowToggle

-0.63

Према

-0.62

elemField

-0.59

addCriterion

-0.56

انجليز

-0.56

 typelib

-0.55

POSITIVE LOGITS

 مشين

0.74

enumi

0.73

 مرئيه

0.71

Hochspringen

0.69

 виправивши

0.69

module

0.66

abestanden

0.63

Datuak

0.61

 harem

0.61

 nahilalakip

0.60

Activations Density 0.005%

references to modules in a programming or documentation context

No Comments

No Known Activations

references to modules in a programming or documentation context

No Comments

No Known Activations