INDEX

Explanations

complex scientific measurements and conditions related to dose-response relationships in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rawDesc

-0.72

 تضيفلها

-0.71

脚注の使い方

-0.67

AnchorStyles

-0.63

 bise

-0.62

তথ্যসূত্র

-0.61

forder

-0.60

 متعلقه

-0.60

 Properly

-0.59

 meilleur

-0.58

POSITIVE LOGITS

(>

0.88

 enough

0.87

 جدًا

0.80

 high

0.78

enough

0.77

 large

0.74

SpringBootTest

0.71

 מאוד

0.70

 heavy

0.66

low

0.62

Activations Density 0.996%

complex scientific measurements and conditions related to dose-response relationships in various contexts

No Comments

No Known Activations