INDEX

Explanations

HTML or template syntax related to structured data and navigation

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

Code-related tokens or symbols

np_acts-logits-general · gemini-2.0-flash

template language constructs

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

XmlAccessType

-0.64

 snippetHide

-0.61

ViewFeatures

-0.60

imageshack

-0.58

তথ্যসূত্র

-0.57

Хьажоргаш

-0.57

astéro

-0.57

Geplaatst

-0.57

 rhestr

-0.56

 архивлан

-0.56

POSITIVE LOGITS

if

0.65

foreach

0.58

include

0.57

if

0.57

fore

0.57

php

0.56

yield

0.51

bsen

0.51

unless

0.51

 EClass

0.50

Activations Density 0.134%

HTML or template syntax related to structured data and navigation

Code-related tokens or symbols

template language constructs

No Comments

No Known Activations

HTML or template syntax related to structured data and navigation

Code-related tokens or symbols

template language constructs

No Comments

No Known Activations