INDEX

Explanations

terms and references related to scientific analysis and results, particularly in relation to data comparisons, expressions, and correlations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

checkNotNull

-0.52

MACHINE

-0.51

χρι

-0.48

 Tole

-0.48

 Lorentz

-0.47

 AssemblyVersion

-0.46

 thanh

-0.45

 peritoneal

-0.45

</tbody>

-0.44

rigal

-0.44

POSITIVE LOGITS

RenderAtEndOf

0.79

 tandis

0.70

 còn

0.69

 sedangkan

0.69

 whereas

0.67

LookAnd

0.66

0.61

 Others

0.61

whereas

0.60

 kasarigan

0.59

Activations Density 1.052%

terms and references related to scientific analysis and results, particularly in relation to data comparisons, expressions, and correlations

No Comments

No Known Activations