INDEX

Explanations

statistical significance indicators and related values in research findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 كومونز

-0.63

 nahilalakip

-0.53

mybatisplus

-0.53

 Shaping

-0.53

úgó

-0.51

 officiers

-0.48

Portály

-0.47

 Nazionale

-0.46

hiasan

-0.45

VolleyError

-0.45

POSITIVE LOGITS

Демографія

0.73

 kasarigan

0.70

 चीज़ों

0.67

__*/

0.65

 ExecuteAsync

0.64

 odkazy

0.62

Chham

0.61

жава

0.59

IBarButtonItem

0.58

 Савезне

0.58

Activations Density 0.379%

statistical significance indicators and related values in research findings

No Comments

No Known Activations