INDEX

Explanations

elements related to user interactions with selections and actions in a user interface context

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

OpenHelper

-0.53

RegistryLite

-0.51

 Gewer

-0.51

Sprintf

-0.51

initializeApp

-0.51

}`}>

-0.49

localVar

-0.49

constant

-0.48

 capitalized

-0.48

 Spins

-0.48

POSITIVE LOGITS

glBindBuffer

0.59

 selections

0.58

 selection

0.58

选中

0.55

 múl

0.55

 surla

0.55

deselect

0.54

wählen

0.53

 target

0.53

rangian

0.52

Activations Density 0.249%

elements related to user interactions with selections and actions in a user interface context

No Comments

No Known Activations