INDEX

Explanations

references to procedural steps and ingredients in recipes

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

AMPTON

-0.41

 jopa

-0.41

ఔ

-0.40

ogram

-0.39

 thought

-0.39

 odkazy

-0.39

regate

-0.38

igre

-0.38

isArray

-0.38

ificacion

-0.37

POSITIVE LOGITS

Datuak

0.78

Péri

0.71

oa̍t

0.70

MethodManager

0.68

PreferredItem

0.68

rawDesc

0.68

titleMargin

0.67

setVerticalGroup

0.67

:][

0.67

AutoField

0.65

Activations Density 0.405%

references to procedural steps and ingredients in recipes

No Comments

No Known Activations