INDEX

Explanations

punctuation marks and special characters used in programming or scripting contexts

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

code identifiers

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

featureID

-0.71

 defaultstate

-0.60

 ſche

-0.58

RegressionTest

-0.56

 HasFactory

-0.54

 itſelf

-0.52

>//

-0.52

 OMITBAD

-0.51

 initComponents

-0.50

Nuorodos

-0.50

POSITIVE LOGITS

AlterField

0.48

ronpa

0.38

zarchiwizowane

0.37

 CreateTagHelper

0.36

ErrUnexpectedEOF

0.36

 numerus

0.33

PrototypeOf

0.31

 relâche

0.30

addCriterion

0.29

把他

0.29

Activations Density 0.022%

punctuation marks and special characters used in programming or scripting contexts

code identifiers

No Comments

No Known Activations