INDEX

Explanations

mathematical expressions or equations involving variables and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 VIAF

-0.62

godic

-0.59

GHIJKLM

-0.58

writerow

-0.53

Snackbar

-0.52

ulon

-0.50

 rest

-0.49

 AppComponent

-0.49

 parseFrom

-0.49

mal

-0.48

POSITIVE LOGITS

存于互联网档案馆

0.70

Kaynakça

0.62

yntaxException

0.62

GraphicsUnit

0.58

 Chry

0.56

ckså

0.55

 réguli

0.55

ltä

0.54

lă

0.54

￡

0.54

Activations Density 0.438%

mathematical expressions or equations involving variables and their relationships

No Comments

No Known Activations