INDEX

Explanations

references to advantages or positive outcomes associated with various subjects

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

 Scully

-0.57

 Stubbs

-0.49

writeString

-0.48

 PLATES

-0.48

 París

-0.48

 Washburn

-0.47

 Schulze

-0.47

 Rowley

-0.47

 &___

-0.46

 Stringer

-0.45

POSITIVE LOGITS

 benefit

1.23

Benefit

1.21

 Benefit

1.20

benefit

1.16

 benefits

1.13

 Benefits

1.07

Benefits

1.02

benefits

0.95

 benefiting

0.93

 BENEFITS

0.92

Activations Density 0.235%

references to advantages or positive outcomes associated with various subjects

No Comments

No Known Activations