INDEX

Explanations

elements related to scientific terminology and 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ViewFeatures

-0.78

 ExecuteAsync

-0.74

 NSCoder

-0.68

extAlignment

-0.67

__":

-0.67

 فريبيس

-0.66

LookAnd

-0.65

UnitTesting

-0.65

Hochspringen

-0.62

########.

-0.62

POSITIVE LOGITS

 antena

0.64

 gloves

0.61

 oven

0.60

 Organ

0.60

 Gloves

0.59

cam

0.59

 Refrigerator

0.58

 magnifying

0.57

 Oven

0.56

 campana

0.56

Activations Density 2.978%

elements related to scientific terminology and research findings

No Comments

No Known Activations