INDEX

Explanations

the word "original" and terms related to programming, files, and versions

oai_token-act-pair · gemini-2.0-flash

original

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 original

-2.69

original

-2.42

Original

-2.36

 Original

-2.30

 originals

-2.05

 ORIGINAL

-2.00

 originales

-1.88

ORIGINAL

-1.82

 originali

-1.78

 originale

-1.77

POSITIVE LOGITS

runApp

0.86

rungsseite

0.83

EndContext

0.77

RenderAtEndOf

0.77

ISupport

0.73

 createState

0.72

UnusedPrivate

0.71

 дописавши

0.69

GEBURTSDATUM

0.69

 Roskov

0.68

Activations Density 8.679%

the word "original" and terms related to programming, files, and versions

original

No Comments

No Known Activations