INDEX

Explanations

code snippets related to data structures and their manipulation in programming contexts

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

autorest.Encode

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

ArgsConstructor

-0.62

 betweenstory

-0.60

RectangleBorder

-0.54

 AssemblyTitle

-0.52

ChildScrollView

-0.50

RegressionTest

-0.47

InSection

-0.45

 surla

-0.44

 Audiodateien

-0.44

principalColumn

-0.43

POSITIVE LOGITS

WireFormatLite

0.54

QMetaType

0.46

ghijklmnop

0.45

 հղումներ

0.45

Schicken

0.44

 gyhoeddwyd

0.43

 Viet

0.43

jspb

0.42

ConstraintMaker

0.42

tatu

0.41

Activations Density 0.046%

code snippets related to data structures and their manipulation in programming contexts

autorest.Encode

No Comments

No Known Activations