INDEX

Explanations

symbols indicating speech or dialogue

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

Mathematical/technical notation and symbols

np_acts-logits-general · gemini-2.0-flash

wrt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

OpenHelper

-0.66

djangoproject

-0.63

queryInterface

-0.60

 насељу

-0.52

LookAnd

-0.52

complexContent

-0.49

arschu

-0.48

();)

-0.48

rawQuery

-0.46

ыгана

-0.46

POSITIVE LOGITS

wixt

0.80

sieme

0.68

enseits

0.67

ardless

0.65

ithin

0.64

 notwithstanding

0.59

rån

0.58

neath

0.58

ůli

0.58

 كومونز

0.57

Activations Density 0.327%

symbols indicating speech or dialogue

Mathematical/technical notation and symbols

wrt

No Comments

No Known Activations