INDEX

Explanations

definite articles and their usage in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

expandindo

-0.49

↵↵↵

-0.43

isContained

-0.40

แรก

-0.40

AsUp

-0.39

 además

-0.34

 другое

-0.33

RTSN

-0.33

 pén

-0.32

 veng

-0.31

POSITIVE LOGITS

 opposite

0.56

 flexib

0.55

 primary

0.55

таратура

0.52

 appliance

0.52

 referrerpolicy

0.51

 muse

0.51

########.

0.50

 fitting

0.48

 duvet

0.48

Activations Density 0.153%

definite articles and their usage in the text

No Comments

No Known Activations

definite articles and their usage in the text

No Comments

No Known Activations