INDEX

Explanations

references to specific "Volume" designations in a collection of works or data sets

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

starting with "Vol" or "Voc"

np_acts-logits-general · gemini-2.0-flash

vol- words

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

bì

-0.51

 supérieures

-0.50

 poitrine

-0.48

prove

-0.47

 indépendante

-0.45

grün

-0.45

 Spitze

-0.45

Fprintf

-0.43

 Prove

-0.43

 figlia

-0.43

POSITIVE LOGITS

 GenerationType

0.95

AutoScale

0.76

 ProtoMessage

0.71

 doInBackground

0.68

complexContent

0.67

 ostavi

0.67

protoimpl

0.63

VOL

0.63

URLException

0.63

ResponseWriter

0.63

Activations Density 0.085%

references to specific "Volume" designations in a collection of works or data sets

starting with "Vol" or "Voc"

vol- words

No Comments

No Known Activations