INDEX

Explanations

references to specific individuals and their contributions 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

late

-0.46

 Croatia

-0.42

force

-0.42

Everything

-0.42

 clearing

-0.40

gama

-0.39

 Everything

-0.39

нивер

-0.38

Working

-0.38

 illet

-0.37

POSITIVE LOGITS

Искәрмәләр

0.70

 getView

0.68

 fieldNum

0.68

AntiForgeryToken

0.67

RepeatedField

0.66

SharedDtor

0.66

CROSSTALK

0.65

ApiProperty

0.64

XmlIgnore

0.64

stateMutability

0.63

Activations Density 0.117%

references to specific individuals and their contributions in various contexts

No Comments

No Known Activations