INDEX

Explanations

words related to preferences and licensing

oai_token-act-pair · gemini-2.0-flash

favorite

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Еще

-1.88

Еще

-1.79

 color

-1.79

 Ее

-1.74

 favorite

-1.74

 labor

-1.73

 behavior

-1.73

 colors

-1.72

behavior

-1.71

 rumor

-1.71

POSITIVE LOGITS

Şi

1.02

Şi

0.92

aturi

0.72

ţ

0.71

 Bucure

0.68

ised

0.66

 tranquill

0.65

atini

0.64

 civilised

0.64

isable

0.63

Activations Density 3.603%

words related to preferences and licensing

favorite

No Comments

No Known Activations