INDEX

Explanations

objects, their classifications, and specific terms or acronyms related to various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

KommentareTeilen

-0.94

 estekak

-0.90

audiovisuel

-0.88

 betweenstory

-0.79

 gynhyrchwyd

-0.79

URLException

-0.79

 propOrder

-0.79

IntoConstraints

-0.76

 فريبيس

-0.76

 المعيارى

-0.75

POSITIVE LOGITS

MemoryWarning

0.54

ks

0.47

paya

0.46

يا

0.45

└

0.44

يره

0.44

кове

0.43

PutMapping

0.43

િક

0.41

co

0.41

Activations Density 1.235%

objects, their classifications, and specific terms or acronyms related to various fields

No Comments

No Known Activations