INDEX

Explanations

conditional phrases that indicate variability or dependence on specific factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

υτό

-0.62

brochen

-0.58

Addo

-0.56

 hereby

-0.56

zwald

-0.55

bius

-0.54

 diatas

-0.52

weg

-0.52

깥

-0.50

 baru

-0.50

POSITIVE LOGITS

 depending

1.49

depending

1.47

Depending

1.39

 Depending

1.37

 Depends

1.26

Depends

1.21

 depends

1.20

depends

1.14

 dependiendo

1.13

 depende

1.08

Activations Density 0.169%

conditional phrases that indicate variability or dependence on specific factors

No Comments

No Known Activations