INDEX

Explanations

snippets of code and examples related to programming instructions

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

code snippets and examples

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

 ſta

-0.38

 faſt

-0.33

 inherited

-0.33

 calculées

-0.32

 themſelves

-0.32

 ſte

-0.31

Samo

-0.31

 anſ

-0.30

createServer

-0.28

🔕

-0.28

POSITIVE LOGITS

 snippetHide

0.81

FormTagHelper

0.71

GOTREF

0.63

msgTypes

0.62

HtmlAttribute

0.60

 ExecuteAsync

0.58

ReusableCell

0.57

 متعلقه

0.57

 illustrative

0.56

 snippets

0.55

Activations Density 0.185%

snippets of code and examples related to programming instructions

code snippets and examples

No Comments

No Known Activations