INDEX

Explanations

references or citations for data sources

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

 TextAppearance

-0.79

Hentet

-0.61

 parseFrom

-0.58

nî

-0.56

 abstrato

-0.55

NgModule

-0.55

SourceChecksum

-0.55

omock

-0.54

dcc

-0.53

ItemBackground

-0.53

POSITIVE LOGITS

etc

0.79

etc

0.68

 تضيفلها

0.63

 others

0.61

others

0.61

AnimationsModule

0.60

Etc

0.58

 Others

0.57

及び

0.56

Etc

0.55

Activations Density 0.922%

references or citations for data sources

No Comments

No Known Activations