INDEX

Explanations

large activation values representing separate sections or segments in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 nakalista

-0.62

IsMutable

-0.62

SourceChecksum

-0.59

 للمعارف

-0.57

 Winaray

-0.55

permum

-0.55

ſelves

-0.54

 števil

-0.54

 invokingState

-0.53

Externé

-0.52

POSITIVE LOGITS

apimachinery

0.73

 name

0.68

 getName

0.65

名称

0.63

 names

0.61

 Name

0.60

name

0.60

 NAME

0.59

 नाम

0.57

getName

0.54

Activations Density 0.142%

large activation values representing separate sections or segments in a document

No Comments

No Known Activations