INDEX

Explanations

structures and formatting in mathematical expressions or arrays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

]').

-0.52

omiast

-0.52

ModelAdmin

-0.52

 }}$}

-0.51

Demografia

-0.51

 Référence

-0.51

endpush

-0.49

 lordship

-0.49

 clocks

-0.49

DockStyle

-0.48

POSITIVE LOGITS

GEBURTSDATUM

1.03

 surla

0.65

adaptiveStyles

0.64

GetAxis

0.57

بوابة

0.57

setVerticalGroup

0.55

tikus

0.52

 AssemblyTitle

0.51

EndProject

0.51

 tabaco

0.50

Activations Density 0.123%

structures and formatting in mathematical expressions or arrays

No Comments

No Known Activations