INDEX

Explanations

references to specific medical or biological terms and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

and

-0.69

</thead>

-0.63

 resourceCulture

-0.54

 however

-0.54

jspx

-0.53

ngdoc

-0.51

 infatti

-0.50

ConstraintMaker

-0.50

*}[

-0.50

 jednak

-0.48

POSITIVE LOGITS

何より

0.66

 therefrom

0.62

 withal

0.62

 Paglinawan

0.59

 tartalomajánló

0.56

 thereof

0.56

 Majefty

0.55

 poveznice

0.53

).__

0.53

 utafitiHapana

0.52

Activations Density 2.879%

references to specific medical or biological terms and their implications

No Comments

No Known Activations