INDEX

Explanations

references to decision-making and personal experiences

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

bcryptjs

-0.53

 للمعارف

-0.50

 الحره

-0.48

Autoritní

-0.47

Hentet

-0.46

 resourceCulture

-0.46

{?>

-0.45

 bør

-0.45

●●

-0.44

 patří

-0.43

POSITIVE LOGITS

 eventually

0.63

eventually

0.52

 became

0.50

Eventually

0.50

 gradually

0.50

 Eventually

0.49

 soon

0.48

 began

0.47

 quickly

0.46

 suddenly

0.45

Activations Density 1.009%

references to decision-making and personal experiences

No Comments

No Known Activations