INDEX

Explanations

the term "scale" and its variations, indicating a focus on scaling concepts within data or programming contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Padova

-0.68

gibt

-0.67

 néglig

-0.67

obby

-0.66

**/

-0.65

🏻

-0.65

 Pute

-0.64

 Чита

-0.64

 bună

-0.64

phite

-0.63

POSITIVE LOGITS

 scales

1.69

 SCALE

1.64

 Scales

1.60

 Scale

1.56

 scale

1.53

Scale

1.52

Scales

1.52

scales

1.46

SCALE

1.45

scale

1.34

Activations Density 0.064%

the term "scale" and its variations, indicating a focus on scaling concepts within data or programming contexts

No Comments

No Known Activations