INDEX

Explanations

file or path references in a code context

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

<start_of_turn> user content

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

InjectAttribute

-0.80

:✨

-0.70

 resourceCulture

-0.67

ScopeManager

-0.62

findpost

-0.61

CloseOperation

-0.61

NameInMap

-0.58

 autorytatywna

-0.55

ArgumentParser

-0.55

 InputDecoration

-0.55

POSITIVE LOGITS

templateUrl

0.51

 wikipagina

0.38

stdafx

0.38

 situe

0.36

sting

0.36

ส

0.35

 tube

0.33

 AssemblyCompany

0.33

 form

0.33

 sociaux

0.33

Activations Density 0.002%

file or path references in a code context

<start_of_turn> user content

No Comments

No Known Activations