INDEX

Explanations

references to function definitions and method calls in code

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

function definitions and `self` usage

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 <>",

-0.64

EDEFAULT

-0.57

ChildScrollView

-0.57

 dAtA

-0.52

uxxxx

-0.51

.*")]

-0.50

 Winaray

-0.50

 '\\;'

-0.50

 esboço

-0.48

webElementXpaths

-0.48

POSITIVE LOGITS

WEBPACK

0.43

Skocz

0.42

፩

0.41

SuppressLint

0.40

 EconPapers

0.39

unhofer

0.39

SneakyThrows

0.38

dflare

0.36

 تضيفلها

0.35

वास

0.34

Activations Density 0.020%

references to function definitions and method calls in code

function definitions and `self` usage

No Comments

No Known Activations