INDEX

Explanations

references to characters or names associated with narrative or storytelling elements

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

Two-letter abbreviations or acronyms

np_acts-logits-general · gemini-2.0-flash

pH, cs, ils, pps, ys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 ModelExpression

-0.83

 AssemblyTitle

-0.69

 بيها

-0.68

GeoNames

-0.65

UrlResolution

-0.61

енча

-0.59

 ostavi

-0.59

FXMLLoader

-0.59

 createState

-0.58

 referenties

-0.57

POSITIVE LOGITS

jfree

0.62

 rifer

0.57

 vedea

0.57

 inteiro

0.55

ônus

0.55

ondheim

0.55

ThroughAttribute

0.55

 rhestr

0.55

 gând

0.53

 Bumble

0.53

Activations Density 1.010%

references to characters or names associated with narrative or storytelling elements

Two-letter abbreviations or acronyms

pH, cs, ils, pps, ys

No Comments

No Known Activations