INDEX

Explanations

phrases indicating significant impact or influence in various contexts

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

architectural researchers biography

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

󠁣

-0.44

帖最后由

-0.43

NOPQRST

-0.41

zufügen

-0.40

ElementException

-0.40

AnimationsModule

-0.39

СТВА

-0.39

MessageOf

-0.39

ismet

-0.39

stateProvider

-0.39

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.48

AISSEE

0.41

gql

0.40

triangleq

0.39

cioso

0.39

brü

0.38

Semi

0.38

träd

0.37

WSGI

0.37

 ویکی‌پدی

0.37

Activations Density 0.013%

phrases indicating significant impact or influence in various contexts

architectural researchers biography

No Comments

No Known Activations