INDEX

Explanations

references to navigation and complex data structures in code

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

test code and Java documentation

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

GEBURTSDATUM

-0.65

GEBURTS

-0.57

+#+#

-0.50

genodigd

-0.50

 surla

-0.46

beiros

-0.46

 Administrativna

-0.45

 Gläub

-0.45

 виправивши

-0.45

 llanto

-0.45

POSITIVE LOGITS

ConstraintMaker

0.54

RegistryLite

0.52

ParallelGroup

0.50

 dAtA

0.46

ThroughAttribute

0.41

㎠

0.36

ﬅ

0.35

AccessException

0.35

ScopeManager

0.35

ruptedException

0.34

Activations Density 0.207%

references to navigation and complex data structures in code

test code and Java documentation

No Comments

No Known Activations