INDEX

Explanations

technical terms related to database operations and optimization

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

Non-English language snippets

np_acts-logits-general · gemini-2.0-flash

backup and restore operations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

</strong>

-0.55

and

-0.52

**

-0.51

المكان

-0.50

*}

-0.46

*}$

-0.45

testens

-0.45

;}

-0.44

 late

-0.44

POSITIVE LOGITS

 الحره

0.80

 بيها

0.77

出版年

0.74

GraphicsUnit

0.72

EndInit

0.69

rentices

0.68

Hentet

0.67

seamnă

0.66

 كومونز

0.66

 fibrillation

0.65

Activations Density 0.066%

technical terms related to database operations and optimization

Non-English language snippets

backup and restore operations

No Comments

No Known Activations