INDEX

Explanations

quantitative data and statistical results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

HtmlAttribute

-0.55

बाह

-0.49

instancetype

-0.44

 Chwiliwch

-0.44

ult

-0.43

を抑

-0.42

cons

-0.42

cyklopedia

-0.41

рона

-0.41

ultra

-0.40

POSITIVE LOGITS

MemoryWarning

0.84

 كومونز

0.65

 tartalomajánló

0.65

 disambiguazione

0.65

QMetaType

0.64

 ProtoMessage

0.64

Vidite

0.61

Personensuche

0.61

StoryboardSegue

0.60

 يتيمه

0.59

Activations Density 0.250%

quantitative data and statistical results

No Comments

No Known Activations