INDEX

Explanations

phrases and terms indicating uniqueness or exclusivity in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 mukaan

-0.40

 Độ

-0.38

 égard

-0.36

overset

-0.35

 Mucha

-0.34

 prest

-0.33

 tahap

-0.33

 eloku

-0.33

aufbau

-0.33

 tremendously

-0.33

POSITIVE LOGITS

satunya

0.82

bootstrapcdn

0.77

 kasarigan

0.70

 einzigen

0.69

 eneste

0.66

SourceChecksum

0.66

 nonUne

0.65

 enige

0.61

唯一

0.61

httphttps

0.60

Activations Density 0.205%

phrases and terms indicating uniqueness or exclusivity in descriptions

No Comments

No Known Activations

phrases and terms indicating uniqueness or exclusivity in descriptions

No Comments

No Known Activations