INDEX

Explanations

variables and identifiers in code sections

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

`<start_of_turn> user`

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

 betweenstory

-0.60

 EconPapers

-0.55

]=>

-0.54

⅘

-0.51

ifflin

-0.50

 noDo

-0.48

 newBuilder

-0.48

 Italijani

-0.48

 Administrativna

-0.48

ंदीखरीदारी

-0.47

POSITIVE LOGITS

الإنجليزية

0.40

 IBOutlet

0.40

VersionUID

0.37

 Chance

0.37

 patin

0.36

 propOrder

0.36

хьтан

0.36

توض

0.36

 MonoBehaviour

0.36

IContainer

0.35

Activations Density 0.002%

variables and identifiers in code sections

`<start_of_turn> user`

No Comments

No Known Activations