INDEX

Explanations

elements related to mathematical and programming constructs

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

Superscript notation and associated symbols

np_acts-logits-general · gemini-2.0-flash

specific identifiers and continuations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

RenderAtEndOf

-0.78

 utafitiHapana

-0.75

 للاسماء

-0.72

apimachinery

-0.71

#+#

-0.70

 MainAxisSize

-0.69

 GenerationType

-0.65

 InputDecoration

-0.63

/\.

-0.62

(!__

-0.62

POSITIVE LOGITS

 Edition

0.70

ๆ

0.64

 EDITION

0.60

мум

0.59

ẵn

0.58

EDEFAULT

0.55

版

0.55

 SIMBAD

0.55

częściej

0.53

دانشنامهٔ

0.52

Activations Density 1.003%

elements related to mathematical and programming constructs

Superscript notation and associated symbols

specific identifiers and continuations

No Comments

No Known Activations