INDEX

Explanations

references to possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Grüsse

-0.57

 Worten

-0.54

inally

-0.54

AxisAlignment

-0.52

digkeit

-0.52

ا

-0.51

entibus

-0.50

 tica

-0.49

 tiens

-0.49

Clik

-0.49

POSITIVE LOGITS

their

0.78

Their

0.78

 their

0.76

<bos>

0.75

 Their

0.68

 THEIR

0.63

 leur

0.60

 jejich

0.58

 Leur

0.56

 leurs

0.56

Activations Density 0.149%

references to possession or ownership

No Comments

No Known Activations