INDEX

Explanations

phrases associated with states of being or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

idenza

-0.53

 loob

-0.52

ніципа

-0.51

 Lingkungan

-0.51

geführten

-0.51

 preuve

-0.50

 ligiloj

-0.50

csolódó

-0.50

 Genuss

-0.49

fony

-0.48

POSITIVE LOGITS

 limbo

0.70

migrationBuilder

0.69

 oblivion

0.68

 pieces

0.67

 ruins

0.65

 flames

0.63

 Pieces

0.60

 obscurity

0.59

 ruin

0.58

VersionUID

0.58

Activations Density 0.378%

phrases associated with states of being or conditions

No Comments

No Known Activations