INDEX

Explanations

job titles and company-related words

oai_token-act-pair · gemini-2.0-flash

leadership

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Referanser

-0.63

 MainAxisSize

-0.60

StoryboardSegue

-0.60

aarrggbb

-0.59

 Voiture

-0.54

 continúas

-0.54

writeFieldEnd

-0.54

 bonfire

-0.53

ereg

-0.51

 Economia

-0.51

POSITIVE LOGITS

 developing

0.63

 expertise

0.60

 professional

0.59

Kariera

0.59

developed

0.59

 developer

0.58

 entwick

0.57

 specialist

0.57

 practising

0.56

 autorytatywna

0.56

Activations Density 1.108%

job titles and company-related words

leadership

No Comments

No Known Activations