INDEX

Explanations

elements related to structured data or programming syntax

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

########.

-0.93



-0.73

rungsseite

-0.72

 تف

-0.68

mid

-0.67

("-

-0.66

mal

-0.65

bro

-0.64

 المعيارى

-0.64

TRY

-0.64

POSITIVE LOGITS

 judiciales

0.66

seamnă

0.65

 politiet

0.63

ngdoc

0.61

randomUUID

0.59

 ་་

0.56

 døde

0.55

migrationBuilder

0.52

)";

0.52

 kuten

0.51

Activations Density 0.614%

elements related to structured data or programming syntax

No Comments

No Known Activations