INDEX

Explanations

programming syntax or structure

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

enumii

-0.36

 coloris

-0.36

səhifə

-0.35

 religieux

-0.34

Portail

-0.34

playerId

-0.32

FXML

-0.32

 QtCore

-0.32

 иму

-0.32

 faisons

-0.30

POSITIVE LOGITS

CreateMap

3.38

AccessorTable

1.08

tagHelperRunner

0.69

 AutoMapper

0.65

 CreateTagHelper

0.61

Personensuche

0.59

SourceChecksum

0.59

 appelez

0.57

TypeMap

0.56

createTable

0.55

Activations Density 0.000%

programming syntax or structure

<start_of_turn>user

No Comments

No Known Activations