INDEX

Explanations

groups of letters and words that commonly occur in scientific publications, such as author names and affiliations, and acknowledgements sections.

oai_token-act-pair · gemini-2.0-flash

scientific citations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

TypedDataSet

-0.54

deelte

-0.48

modelBuilder

-0.47

 continúas

-0.44

FlatAppearance

-0.44

BASEPATH

-0.43

Rüyada

-0.43

gameserver

-0.42

RenderAtEndOf

-0.41

Források

-0.40

POSITIVE LOGITS

ussis

0.61

ällor

0.59

 typelib

0.57

Spend

0.56

TintMode

0.56

Zag

0.54

 civile

0.53

ibouti

0.52

hesus

0.52

AppCompatTheme

0.51

Activations Density 0.925%

groups of letters and words that commonly occur in scientific publications, such as author names and affiliations, and acknowledgements sections.

scientific citations

No Comments

No Known Activations