INDEX

Explanations

words indicating relative size or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 McIl

-0.58

endregion

-0.56

epy

-0.55

 équipée

-0.55

ijão

-0.54

ី

-0.53

 čet

-0.53

 poussière

-0.53

orteur

-0.53

headless

-0.53

POSITIVE LOGITS

 bigger

1.56

 biggest

1.38

biggest

1.35

bigger

1.35

 Bigger

1.33

 Biggest

1.33

Biggest

1.29

Bigger

1.19

 larger

1.03

 largest

1.00

Activations Density 0.088%

words indicating relative size or significance

No Comments

No Known Activations

words indicating relative size or significance

No Comments

No Known Activations