INDEX

Explanations

references to functions and properties within classes in programming

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

this paper

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 Roskov

-0.62

oredCriteria

-0.62

 malah

-0.61

rungsseite

-0.59

InitVars

-0.58

 inclusions

-0.56

Spoljašnje

-0.55

ьаж

-0.54

Và

-0.54

twimg

-0.54

POSITIVE LOGITS

 متعلقه

0.71

المناصب

0.65

ornadas

0.60

 typelib

0.60

 InputDecoration

0.57

 Chon

0.56

/*

0.55

//

0.52

IZA

0.52

 Tapa

0.51

Activations Density 0.005%

references to functions and properties within classes in programming

this paper

No Comments

No Known Activations