INDEX

Explanations

verbs indicating decisions or choices being made

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

 movi

-0.36

Weblinks

-0.35

 capacity

-0.35

 minuta

-0.35

kny

-0.35

 exac

-0.34

 errors

-0.34

 mastery

-0.34

Errors

-0.33

Already

-0.33

POSITIVE LOGITS

styleType

0.78

 decided

0.76

decided

0.73

 opted

0.71

 chose

0.67

ftagPool

0.66

 decidido

0.66

WriteBarrier

0.66

EDEFAULT

0.65

chose

0.65

Activations Density 0.367%

verbs indicating decisions or choices being made

No Comments

No Known Activations