INDEX

Explanations

patterns or structures in data that may represent logical or structured organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

marle

-0.56

NYC

-0.55

ntag

-0.55

 Borough

-0.55

 NYPD

-0.53

 Middletown

-0.53

nyc

-0.53

 Benedetto

-0.53

 Appalachian

-0.52

voor

-0.52

POSITIVE LOGITS

netbeans

0.85

ftagPool

0.77

 defaultstate

0.72

 >=",

0.69

Sask

0.68

Personensuche

0.67

ManagedBean

0.67

TypedDataSet

0.66

 Saskatoon

0.64

TAWA

0.63

Activations Density 0.076%

patterns or structures in data that may represent logical or structured organization

No Comments

No Known Activations