INDEX

Explanations

instances of the English language and related terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uppertal

-1.03

kz

-0.81

 архивлан

-0.78

 vpon

-0.76

 Seeder

-0.76

SBATCH

-0.76

 parseFrom

-0.75

 Victims

-0.74

 Thayer

-0.74

 дописавши

-0.73

POSITIVE LOGITS

 English

1.42

 ENGLISH

1.23

English

1.13

 Engl

1.12

 England

1.10

 english

1.03

 engl

0.99

ENGLISH

0.98

England

0.96

Engl

0.93

Activations Density 0.053%

instances of the English language and related terms

No Comments

No Known Activations