INDEX

Explanations

code snippets and annotations related to programming and software development

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ***!

-0.67

Suara

-0.63

Bioaccumulative

-0.63

CppMethod

-0.58

 OnTrigger

-0.50

öte

-0.48

 Himo

-0.48

roek

-0.48

خصة

-0.47

 namin

-0.47

POSITIVE LOGITS

=[];

0.68

InstanceState

0.65

примеча

0.63

contentView

0.61

 Governing

0.61

esen

0.59

:[]

0.58

GEBURTSDATUM

0.58

Activations Density 2.577%

code snippets and annotations related to programming and software development

No Comments

No Known Activations