INDEX

Explanations

technical terms, variables, and references in programming and documentation contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

tagHelperRunner

-0.76

ViewFeatures

-0.68

DockStyle

-0.62

 الحره

-0.58

SourceChecksum

-0.58

routeProvider

-0.58

AutoScaleMode

-0.57

FormUrlEncoded

-0.57

setHorizontal

-0.56

PhysRev

-0.55

POSITIVE LOGITS

rrggbb

0.59

itively

0.55

ůli

0.53

lillah

0.49

ushka

0.49

edly

0.49

 slutt

0.48

 Sawyer

0.48

 formid

0.48

endwhile

0.48

Activations Density 1.571%

technical terms, variables, and references in programming and documentation contexts

No Comments

No Known Activations