INDEX

Explanations

terms related to measurements and comparisons in medical or biological contexts

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

ритори

-0.60

 فريبيس

-0.57

addContainerGap

-0.57

 BoxDecoration

-0.55

 Spoilers

-0.54

 <>",

-0.54

piram

-0.51

@"/

-0.50

 AttributeSet

-0.50

BufferException

-0.49

POSITIVE LOGITS

 AssemblyCulture

0.77

жнему

0.62

 elsewhere

0.60

Erreferentziak

0.59

 other

0.58

 regolare

0.58

 achtergrond

0.57

 unrelated

0.57

 referenties

0.57

 ohnehin

0.57

Activations Density 0.576%

terms related to measurements and comparisons in medical or biological contexts

No Comments

No Known Activations