INDEX

Explanations

punctuation indicating dialogue or spoken phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 afin

-0.51

рного

-0.49

레이

-0.49

 Nickel

-0.48

لاب

-0.48

 weather

-0.48

ồn

-0.48

pho

-0.47

Sul

-0.47

 vég

-0.47

POSITIVE LOGITS

SBATCH

0.87

 AssemblyTitle

0.81

BeginContext

0.78

SpringBootTest

0.78

ckeye

0.74

fara

0.74

udadera

0.72

ocardial

0.71

 resourceCulture

0.69

})*/

0.68

Activations Density 0.095%

punctuation indicating dialogue or spoken phrases

No Comments

No Known Activations