INDEX

Explanations

code or programming-related elements and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

SourceChecksum

-0.75

ViewImports

-0.67

="@+

-0.65

DockStyle

-0.64

endwhile

-0.60

 estimés

-0.59

CppMethod

-0.58

Portail

-0.58

 ویکی‌آمباردا

-0.58

 disambiguazione

-0.57

POSITIVE LOGITS

 scala

0.71

Seq

0.71

Seq

0.66

implicit

0.66

scala

0.66

 implicitly

0.63

 scal

0.62

 implicit

0.61

 Scala

0.60

Scala

0.58

Activations Density 0.125%

code or programming-related elements and structures

No Comments

No Known Activations