INDEX

Explanations

the name 'Al' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Hochspringen

-0.85

 ―――――

-0.83

Jü

-0.77

 ་་

-0.76

 itſelf

-0.76

 surfact

-0.75

 raiſ

-0.75

StructEnd

-0.73

 Theſe

-0.73

 Phry

-0.72

POSITIVE LOGITS

Al

3.26

Al

2.86

AL

2.28

al

2.21

AL

1.51

 Ал

1.43

 Аль

1.40

アル

1.38

Ал

1.30

Аль

1.27

Activations Density 0.072%

the name 'Al' in various contexts

No Comments

No Known Activations