INDEX

Explanations

patterns or structures in hierarchical data or formatting

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

javascript/java/c++ code snippets

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

 незавершена

-0.57

addCriterion

-0.50

ьаж

-0.47

 Paglinawan

-0.46

 AssemblyCulture

-0.44

 kasarigan

-0.42

 <=",

-0.42

featureID

-0.41

 IFTT

-0.41

מבר

-0.41

POSITIVE LOGITS

MessageOf

0.54

SizeF

0.43

RegressionTest

0.42

RenderAtEndOf

0.40

تقاوى

0.38

instancetype

0.38

 disambiguazione

0.38

༘

0.37

meia

0.36

WSGI

0.36

Activations Density 0.034%

patterns or structures in hierarchical data or formatting

javascript/java/c++ code snippets

No Comments

No Known Activations