INDEX

Explanations

text formatted as code or programming language syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ChildScrollView

-0.77

ViewById

-0.58

FailureListener

-0.57

antMatchers

-0.57

 nowhere

-0.57

AndroidJUnit

-0.57

 propOrder

-0.56

υμα

-0.55

zzlement

-0.55

 defStyleAttr

-0.55

POSITIVE LOGITS

 Lightboxes

0.67

 -->>

0.55

—

0.55

findpost

0.53

webElementXpaths

0.49

例句

0.48

middels

0.47

 出版

0.46

+:+

0.46

 whofe

0.46

Activations Density 0.018%

text formatted as code or programming language syntax

No Comments

No Known Activations