INDEX

Explanations

code-related syntactic structures, particularly brackets, semicolons, and function definitions

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

Code punctuation and brackets

np_acts-logits-general · gemini-2.0-flash

code block delimiters

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 clearColor

-0.64

++

-0.62

 whiteColor

-0.61

 XNUMX

-0.59

 Smar

-0.58

viewWillAppear

-0.57

iD

-0.56

glBegin

-0.55

 userSchema

-0.55

 kuiten

-0.53

POSITIVE LOGITS

帖最后由

0.85

sizeCache

0.74

AutoScaleMode

0.74

__["

0.73

IndentedString

0.73

تقاوى

0.68

roglo

0.67

if

0.66

UnsafeEnabled

0.66

 mijne

0.65

Activations Density 0.259%

code-related syntactic structures, particularly brackets, semicolons, and function definitions

Code punctuation and brackets

code block delimiters

No Comments

No Known Activations