INDEX

Explanations

academic titles and degrees

oai_token-act-pair · gemini-2.0-flash

academic titles and degrees

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

 дописавши

-0.75

 ModelExpression

-0.73

 PicClick

-0.72

DockStyle

-0.68

bestos

-0.66

expandindo

-0.66

########.

-0.64

InSection

-0.63

 Voyages

-0.63

ContentAsync

-0.63

POSITIVE LOGITS

 degree

0.79

 degrees

0.68

 Degree

0.64

PhD

0.63

degree

0.62

 doctorate

0.56

Degree

0.54

estría

0.52

 üzer

0.52

degrees

0.50

Activations Density 0.801%

academic titles and degrees

academic titles and degrees

No Comments

No Known Activations