INDEX

Explanations

elements related to mathematical definitions and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

HHHH

-0.77

NUK

-0.75

alth

-0.71

kook

-0.71

afo

-0.70

gress

-0.70

ArrowToggle

-0.70

Zuz

-0.70

igate

-0.70

cuc

-0.69

POSITIVE LOGITS

 princesas

0.71

 Italij

0.67

 Recuperado

0.67

 navideño

0.64

 quizá

0.64

 Straus

0.63

 enfermera

0.62

 Moscú

0.61

 thermique

0.60

 montañas

0.60

Activations Density 2.104%

elements related to mathematical definitions and notations

No Comments

No Known Activations