INDEX

Explanations

annotations and metadata in code, particularly those related to parameters and return types

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

code documentation param

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

TagHelper

-0.32

LLocation

-0.30

fromUtf

-0.30

ンダント

-0.30

DoubleQuotes

-0.29

bolista

-0.29

друг

-0.29

 inscription

-0.29

ViewImports

-0.29

migrationBuilder

-0.28

POSITIVE LOGITS

évaluateur

0.61

GEBURTSDATUM

0.58

SharedCtor

0.52

клопе

0.52

 JADX

0.51

₁)

0.51

ASX

0.49

 Bilateral

0.49

IsMutable

0.49

の違い

0.49

Activations Density 0.004%

annotations and metadata in code, particularly those related to parameters and return types

code documentation param

No Comments

No Known Activations