INDEX

Explanations

specific institutions, organizations, or notable individuals

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

Capitalized words or brand names

np_acts-logits-general · gemini-2.0-flash

brand names followed by specific products or actions

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

verwijspagina

-0.63

Rüyada

-0.56

oa̍t

-0.55

Autoritní

-0.53

хьтан

-0.51

cals

-0.51

 Roskov

-0.48

payers

-0.47

 reason

-0.47

Seh

-0.47

POSITIVE LOGITS

 صوتيه

0.82

LookAnd

0.73

®-

0.66

 xoay

0.65

 يتيمه

0.64

reportWebVitals

0.63

®

0.62

 cref

0.62

 الحره

0.62

esque

0.61

Activations Density 0.719%

specific institutions, organizations, or notable individuals

Capitalized words or brand names

brand names followed by specific products or actions

No Comments

No Known Activations