INDEX

Explanations

phrases indicating addition or inclusion of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 mesmas

-0.63

 wikipagina

-0.59

 dokonce

-0.55

 selanjutnya

-0.52

 Bahkan

-0.52

 resourceCulture

-0.51

 invece

-0.51

また

-0.51

 forhold

-0.50

 néz

-0.50

POSITIVE LOGITS

 being

1.37

being

1.19

Being

1.01

 Being

0.97

 BEING

0.96

 étant

0.89

 having

0.80

 those

0.78

 bein

0.78

RectangleBorder

0.76

Activations Density 0.135%

phrases indicating addition or inclusion of information

No Comments

No Known Activations