INDEX

Explanations

programming-related method calls and operations

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

Code and math-related terms

np_acts-logits-general · gemini-2.0-flash

function calls and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 للمعارف

-0.65

AccessorTable

-0.55

TabIndex

-0.54

PostInfinity

-0.53

sizeCache

-0.52

(/^

-0.51

findpost

-0.51

ScopeManager

-0.50

([],

-0.50

 protoimpl

-0.50

POSITIVE LOGITS

berdayakan

0.66

noinspection

0.65

 GenerationType

0.64

 larmes

0.61

 supérieures

0.60

erráneo

0.59

 snippetHide

0.58

 alimentaires

0.57

 intitulé

0.57

reszcie

0.57

Activations Density 0.103%

programming-related method calls and operations

Code and math-related terms

function calls and programming constructs

No Comments

No Known Activations