INDEX

Explanations

function return statements and their types in code documentation

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

function return annotation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 AssemblyTitle

-0.67

SerializedName

-0.61

OGND

-0.61

webElement

-0.60

 userSchema

-0.58

mybatisplus

-0.58

zzleHttp

-0.56

PerformLayout

-0.56

 CommonModule

-0.53

 queſta

-0.52

POSITIVE LOGITS

returns

0.77

 returns

0.71

 return

0.59

 Returns

0.58

Returns

0.56

return

0.56

返回

0.56

 result

0.53

Return

0.52

 returned

0.52

Activations Density 0.011%

function return statements and their types in code documentation

function return annotation

No Comments

No Known Activations