INDEX

Explanations

HTML or XML elements and attributes

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

<start_of_turn> user followed by code

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

gun

-0.41

 Bast

-0.34

 slip

-0.32

 receitas

-0.32

job

-0.31

paddingBottom

-0.31

 Brun

-0.30

DECL

-0.30

 Cahill

-0.30

dcmtk

-0.30

POSITIVE LOGITS

 getApp

0.84

adaptiveStyles

0.77

mybatisplus

0.71

PreferredItem

0.69

msgTypes

0.68

 snippetHide

0.62

contentLoaded

0.62

RectangleBorder

0.60

aarrggbb

0.60

⤹

0.60

Activations Density 0.004%

HTML or XML elements and attributes

<start_of_turn> user followed by code

No Comments

No Known Activations