INDEX

Explanations

expressions related to statistical comparisons and increases or decreases in values or measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

후

-0.54

addGap

-0.52

κίνη

-0.50

Rey

-0.50

SequentialGroup

-0.49

+:+

-0.49

SAE

-0.49

utentic

-0.49

 OnInit

-0.48

 affaire

-0.48

POSITIVE LOGITS

 doubling

0.66

دانشنامهٔ

0.65

 doubled

0.64

Демографія

0.64

KommentareTeilen

0.62

 betweenstory

0.62

 lipat

0.60

 становника

0.59

IsContent

0.58

SerializedSize

0.56

Activations Density 0.308%

expressions related to statistical comparisons and increases or decreases in values or measures

No Comments

No Known Activations