INDEX

Explanations

code-related function definitions and variable handling

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

IsContent

-0.70

<eos>

-0.48

PropertyGroup

-0.41

こともあり

-0.41

PYX

-0.41

 ویکی‌پدی

-0.41

</tbody>

-0.40

DeclareMath

-0.40

 social

-0.39

piv

-0.39

POSITIVE LOGITS

 chré

0.85

 mourut

0.75

 acrylique

0.72

 Daß

0.71

Efq

0.70

 caufe

0.70

 défaite

0.69

 muß

0.68

MultipartFile

0.68

paroles

0.68

Activations Density 1.627%

code-related function definitions and variable handling

No Comments

No Known Activations