INDEX

Explanations

programming-related syntax elements and identifiers

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

<start_of_turn>user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

RegressionTest

-0.51

FieldBuilder

-0.42

__":

-0.41

BeanUtils

-0.40

Autoritní

-0.40

*)&

-0.36

queryInterface

-0.35

 cốc

-0.34

Period

-0.34

uns

-0.34

POSITIVE LOGITS

 viewType

1.02

viewType

0.91

 الرياضيه

0.72

ViewType

0.60

 kasarigan

0.58

MigrationBuilder

0.57

ViewFeatures

0.56

Demografie

0.55

 AssemblyTitle

0.52

 wireType

0.51

Activations Density 0.001%

programming-related syntax elements and identifiers

<start_of_turn>user

No Comments

No Known Activations