INDEX

Explanations

programming constructs related to function definitions and return statements

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

Code snippets with brackets and symbols

np_acts-logits-general · gemini-2.0-flash

array constructors

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

DeleteBehavior

-0.80

IntoConstraints

-0.75

">—

-0.68

oredCriteria

-0.68

AndEndTag

-0.67

contentLoaded

-0.67

Clik

-0.65

 OFDb

-0.63

migrationBuilder

-0.63

LookAnd

-0.62

POSITIVE LOGITS

 array

0.80

array

0.76

compact

0.69

 compact

0.68

 reparations

0.59

["

0.57

["

0.56

Compact

0.53

['

0.53

 reparation

0.50

Activations Density 0.082%

programming constructs related to function definitions and return statements

Code snippets with brackets and symbols

array constructors

No Comments

No Known Activations