INDEX

Explanations

identifications and descriptions of individuals, particularly in a sporting or performance context

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

Климат

-0.75

 itself

-0.61

elerik

-0.59

Rüyada

-0.55

これも

-0.53

InputBorder

-0.53

XmlEnum

-0.53

GOTREF

-0.53

 AssemblyCompany

-0.52

SharedDtor

-0.51

POSITIVE LOGITS

EndTag

0.62

 Actor

0.61

 actor

0.60

ंदीखरीदारी

0.59

 conocido

0.59

mapStateToProps

0.58

Actor

0.58

 serine

0.57

 multinational

0.57

 sinh

0.55

Activations Density 0.320%

identifications and descriptions of individuals, particularly in a sporting or performance context

No Comments

No Known Activations