INDEX

Explanations

function-related keywords and identifiers in programming contexts

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

function definition followed by arguments

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

 виправивши

-0.84

+#+#

-0.67

#+#

-0.65

Diweddarwch

-0.65

 MainAxisSize

-0.64

 Biôgrafia

-0.63

 tartalomajánló

-0.63

principalColumn

-0.62

 defaultstate

-0.61

 Roskov

-0.59

POSITIVE LOGITS

 function

0.43

 role

0.43

function

0.41

 effect

0.40

Role

0.39

SCE

0.39

un

0.39

ElementException

0.39

Mer

0.38

role

0.38

Activations Density 0.009%

function-related keywords and identifiers in programming contexts

function definition followed by arguments

No Comments

No Known Activations