INDEX

Explanations

punctuation marks and formatting indicators in text

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

References within brackets

np_acts-logits-general · gemini-2.0-flash

citation markers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

GraphicsUnit

-0.81

findpost

-0.77

 оригіналу

-0.74

CloseOperation

-0.70

occhi

-0.67

WriteAttribute

-0.67

Jag

-0.66

Tazama

-0.66

Pil

-0.62

 Mell

-0.60

POSITIVE LOGITS

ագրություններ

0.80

 juridiques

0.74

 mallorca

0.74

Efq

0.73

 budapest

0.71

তথ্যসূত্র

0.70

 sauvages

0.70

 kasarigan

0.68

 bogotá

0.67

Kiy

0.65

Activations Density 1.247%

punctuation marks and formatting indicators in text

References within brackets

citation markers

No Comments

No Known Activations