INDEX

Explanations

words related to healthcare or technology companies

oai_token-act-pair · gemini-2.0-flash

mology

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

Negative Logits

 beginnetje

-0.60

Personensuche

-0.50

 continúas

-0.50

 Normdatei

-0.48

kesan

-0.47

UNDEFINED

-0.47

intios

-0.47

transQ

-0.47

nloa

-0.45

Demografie

-0.44

POSITIVE LOGITS

ientôt

0.75

CloseOperation

0.73

UnusedPrivate

0.72

 GoogleFonts

0.71

HomeAsUp

0.69

nolia

0.69

HtmlAttribute

0.68

SPATH

0.66

 Referential

0.63

usermodel

0.63

Activations Density 1.345%

words related to healthcare or technology companies

mology

No Known Activations