INDEX

Explanations

terms related to scaling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

**/

-0.67

RetentionPolicy

-0.61

AndEndTag

-0.59

__*/

-0.58

ifolium

-0.56

ICIENCY

-0.56

'][$

-0.55

Gemeinden

-0.55

wój

-0.54

🏽

-0.54

POSITIVE LOGITS

 Scales

1.38

 scales

1.37

Scales

1.30

 SCALE

1.27

 Scale

1.22

scales

1.20

Scale

1.15

SCALE

1.14

 scale

1.09

 Scal

1.06

Activations Density 0.080%

terms related to scaling

No Comments

No Known Activations