INDEX

Explanations

text about community organizations and non-profits, including their activities and structures

oai_token-act-pair · gemini-2.0-flash

Art

np_token-act-pair-logits · gemini-2.0-flash

organizations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

󠁢

-0.73

 AssemblyCompany

-0.71

ScopeManager

-0.63

ніципалі

-0.61

nonatomic

-0.60

protoimpl

-0.59

 indisponible

-0.57

 nakalista

-0.57

fromCharCode

-0.56

पया

-0.56

POSITIVE LOGITS

 tournament

0.52

web

0.51

 copies

0.50

losa

0.49

 workshop

0.48

ينات

0.47

ateg

0.47

 rubric

0.47

 vorm

0.46

Atra

0.46

Activations Density 3.036%

text about community organizations and non-profits, including their activities and structures

Art

organizations

No Comments

No Known Activations