INDEX

Explanations

references to familial relationships and properties associated with them

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

heden

-0.51

าย

-0.50

種

-0.44

 Figure

-0.43

for

-0.43

TTE

-0.42

atac

-0.41

óta

-0.41

को

-0.41

akit

-0.41

POSITIVE LOGITS

MigrationBuilder

1.15

">//

0.79

astéro

0.78

+#+

0.76

contentLoaded

0.73

Gön

0.71

 EconPapers

0.71

ⓧ

0.71

bcryptjs

0.69

रीदारी

0.68

Activations Density 0.150%

references to familial relationships and properties associated with them

No Comments

No Known Activations