INDEX

Explanations

proper nouns and names associated with individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Monfieur

-0.91

 Châ

-0.87

 Barnabas

-0.83

 blumen

-0.82

 gari

-0.81

 crayfish

-0.80

 Bren

-0.80

 Aene

-0.78

 excit

-0.78

ADM

-0.78

POSITIVE LOGITS

ViewChild

0.87

SourceChecksum

0.85

لينكات

0.84

 kaynağından

0.84

Wy

0.81

Bul

0.79

lamb

0.78

fog

0.75

wy

0.74

bul

0.73

Activations Density 0.633%

proper nouns and names associated with individuals or entities

No Comments

No Known Activations