INDEX

Explanations

terms related to classification and grouping

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

Followed by categories, groups, parts, sections, or clusters

np_acts-logits-general · gemini-2.0-flash

number of groups or phases

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

 ComVisible

-0.69

 referenties

-0.69

XmlAccessType

-0.62

 <=",

-0.58

ագրություններ

-0.58

rungsseite

-0.58

 utafitiHapana

-0.54

toys

-0.53

ItemBackground

-0.52

rawDesc

-0.52

POSITIVE LOGITS

 main

1.17

 categories

1.08

 phases

0.97

 major

0.95

 components

0.95

 stages

0.94

 types

0.92

main

0.81

 basic

0.81

 principaux

0.80

Activations Density 0.563%

terms related to classification and grouping

Followed by categories, groups, parts, sections, or clusters

number of groups or phases

No Comments

No Known Activations