INDEX

Explanations

references to policies or statements that imply a starting point or introduction

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

Follows specific punctuation or symbols

np_acts-logits-general · gemini-2.0-flash

scientific and technical terms

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

StoryboardSegue

-0.92

Expedia

-0.61

tdessen

-0.59

lepaskan

-0.59

 Nacionales

-0.59

 abstrait

-0.58

 religieuses

-0.58

setViewportView

-0.57

.*")]

-0.56

POSITIVE LOGITS

“

0.45

0.44

webElementXpaths

0.39

rovnik

0.37

awaiter

0.37

‘

0.37

Vidite

0.36

htdocs

0.36

коно

0.35

SITE

0.35

Activations Density 0.663%

references to policies or statements that imply a starting point or introduction

Follows specific punctuation or symbols

scientific and technical terms

No Comments

No Known Activations