INDEX

Explanations

mathematical expressions and calculations involving variables

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

let and suppose

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

verifyException

-0.54

UnusedPrivate

-0.53

ThroughAttribute

-0.50

ViewFeatures

-0.50

WriteAttribute

-0.48

 Roskov

-0.48

usermodel

-0.47

TagHelper

-0.47

 Meksiku

-0.46

parsedMessage

-0.46

POSITIVE LOGITS

DebuggerStep

0.45

Cyfeiriadau

0.34

әрмәләр

0.32

Tracce

0.32

 inspection

0.31

 çat

0.30

 magnética

0.30

SPJ

0.30

two

0.30

MEDIA

0.29

Activations Density 0.125%

mathematical expressions and calculations involving variables

let and suppose

No Comments

No Known Activations