INDEX

Explanations

terms related to graphical rendering settings, particularly shadows and textures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

HtmlAttribute

-0.61

 GenerationType

-0.56

 フリー

-0.53

IndentedString

-0.53

RegressionTest

-0.53

Karakteristik

-0.52

styleType

-0.51

GeneratedCode

-0.49

featureID

-0.48

má

-0.48

POSITIVE LOGITS

ArrowToggle

0.63



0.56

 Turnbull

0.54

alitions

0.54

 Tiefe

0.51

utilisons

0.51

entai

0.51

бята

0.50

 AssemblyCompany

0.49

 Bastard

0.49

Activations Density 0.157%

terms related to graphical rendering settings, particularly shadows and textures

No Comments

No Known Activations