INDEX

Explanations

function calls and closures in code

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

closing parentheses and semicolons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

LEGGI

-0.46

 gezegd

-0.44

 invece

-0.43

 ddelweddau

-0.43

 Ausstattung

-0.42

 pula

-0.42

 Absch

-0.42

Билгалдахарш

-0.42

 Erkennt

-0.41

AddWithValue

-0.41

POSITIVE LOGITS



0.61

 autorytatywna

0.59

parsedMessage

0.57

SharedDtor

0.56

VIAF

0.54

новниш

0.50

 snippetHide

0.50

principalTable

0.49

 pinulongan

0.49

Попис

0.45

Activations Density 0.013%

function calls and closures in code

closing parentheses and semicolons

No Comments

No Known Activations