INDEX

Explanations

references to notable individuals or their achievements

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

<start_of_turn>user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

ingeki

-0.35

ėl

-0.34

 Füßen

-0.33

cribir

-0.32

 Keuangan

-0.32

umpang

-0.32

 אופ

-0.31

ukseen

-0.31

ætter

-0.30

 Küste

-0.30

POSITIVE LOGITS

 للمعارف

0.66

Cyfarwyddwr

0.65

addCriterion

0.60

 المعيارى

0.58

 виправивши

0.56

ьаж

0.52

uxxxx

0.52

EDEFAULT

0.51

DoubleQuotes

0.51

ViewFeatures

0.51

Activations Density 0.045%

references to notable individuals or their achievements

<start_of_turn>user

No Comments

No Known Activations