INDEX

Explanations

words related to programming concepts and application management

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

added, modifying, placing, exit

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 &___

-0.52

|()

-0.41

 Prompt

-0.37

AppMethodBeat

-0.35

 Appeals

-0.35

号

-0.35

 independiente

-0.35

jspx

-0.35

ooga

-0.35

>");

-0.35

POSITIVE LOGITS

قایناقلار

0.52

 onCreateView

0.50

 typelib

0.48

bootstrapcdn

0.46

brainly

0.46

bastien

0.45

Personendaten

0.44

 contextLoads

0.42

 ProtoMessage

0.42

 defaultstate

0.42

Activations Density 0.031%

words related to programming concepts and application management

added, modifying, placing, exit

No Comments

No Known Activations