INDEX

Explanations

the start of a document and track structural indicators within the text

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pinulongan

-0.58

lapsingToolbar

-0.54

itura

-0.52

ISCO

-0.48

illet

-0.47

->__

-0.47

udar

-0.46

 living

-0.46

tift

-0.46

Dem

-0.46

POSITIVE LOGITS

 дописавши

0.73

\}\\

0.68

Datuak

0.67

saraba

0.66

OptionsMenu

0.62

 digress

0.62

 nevoie

0.55

 Countess

0.55

Latch

0.53

 lenker

0.53

Activations Density 0.021%

the start of a document and track structural indicators within the text

No Comments

No Known Activations