INDEX

Explanations

code snippets related to programming structures or logic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 insights

-0.54

===

-0.51

 actionable

-0.49

<?>>

-0.47

 livestream

-0.45

!==

-0.45

 nuanced

-0.44

 Insights

-0.44

slf

-0.44

||

-0.44

POSITIVE LOGITS

 Мексичка

0.85

djangoproject

0.83

 InputDecoration

0.83

 refusé

0.78

AndEndTag

0.73

kháu

0.73

 pardoned

0.69

 mariée

0.69

uxxxx

0.68

URLException

0.67

Activations Density 0.079%

code snippets related to programming structures or logic

No Comments

No Known Activations