INDEX

Explanations

sentences that express conditionality or possibility

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personensuche

-0.81

 externi

-0.60

ImageContext

-0.60

 getGroup

-0.57

TypeDef

-0.55

 betweenstory

-0.54

ViewImports

-0.53

TabView

-0.53

IMPORTED

-0.52

 actionPerformed

-0.51

POSITIVE LOGITS

 anyway

0.60

ArgumentParser

0.59

 Plus

0.58

むしろ

0.57

 Moreover

0.54

Plus

0.54

 Worst

0.53

更何况

0.52

 Reste

0.52

 anyways

0.52

Activations Density 0.450%

sentences that express conditionality or possibility

No Comments

No Known Activations