INDEX

Explanations

numerical expressions and counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

SequentialGroup

-0.88

-0.82

FormTagHelper

-0.73

 AssemblyCulture

-0.72

 invokevirtual

-0.71

 propOrder

-0.71

 VIAF

-0.70

ParallelGroup

-0.70

 Paglinawan

-0.69

__*/

-0.69

POSITIVE LOGITS

 peur

0.49

 versa

0.46

FUENTE

0.45

बंध

0.45

vedades

0.43

 cantit

0.43

 Zufall

0.43

lihatan

0.42

anniversaire

0.42

 enrique

0.41

Activations Density 0.021%

numerical expressions and counts

No Comments

No Known Activations