INDEX

Explanations

code-related expressions and structures involving variables and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 مشين

-0.68

 estimés

-0.65

%/

-0.60

 esterni

-0.57

 kasarigan

-0.56

++);

-0.56

__":

-0.55

әһ

-0.52

---*/

-0.52

(")");

-0.52

POSITIVE LOGITS

WireFormatLite

0.82

SBATCH

0.71

didSet

0.70

 eikä

0.64

 melainkan

0.61

 élevées

0.59

 ataupun

0.56

 préfé

0.55

XmlAccessType

0.55

 enfans

0.54

Activations Density 0.562%

code-related expressions and structures involving variables and function definitions

No Comments

No Known Activations