INDEX

Explanations

important nouns and their relationships in various contexts

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

events of, features that

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

portál

-0.42

rove

-0.34

 Anſ

-0.34

diğini

-0.34

unconfirmed

-0.34

Tack

-0.33

 vectorielles

-0.33

Invalid

-0.32

 france

-0.32

TRAILING

-0.32

POSITIVE LOGITS

__':

0.65

 Roskov

0.56

Geplaatst

0.56

CloseOperation

0.55

 '\\;'

0.54

thâu

0.53

 ویکی‌پدی

0.52

 sumpay

0.50

 lacking

0.49

fjspx

0.49

Activations Density 0.406%

important nouns and their relationships in various contexts

events of, features that

No Comments

No Known Activations