INDEX

Explanations

mentions of URLs and web addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Wiktionnaire

-0.60

addCriterion

-0.56

 MonoBehaviour

-0.55

CWE

-0.54

 "..\..\..\

-0.53

subpackage

-0.53

FXML

-0.52

 "..\..\

-0.52

нент

-0.50

atrician

-0.50

POSITIVE LOGITS

com

0.69

comfor

0.68

org

0.56

comand

0.55

govor

0.52

лябин

0.48

 ويكي

0.47

com

0.47

pezi

0.45

edu

0.45

Activations Density 0.229%

mentions of URLs and web addresses

No Comments

No Known Activations