INDEX

Explanations

words related to spiders and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 MotionEvent

-0.58

Espèce

-0.53

PreferredItem

-0.52

abstractmethod

-0.51

 Salgado

-0.50

허

-0.50

Betyg

-0.49

 arşivlendi

-0.48

 Inventors

-0.48

 bezeichneter

-0.47

POSITIVE LOGITS

ParallelGroup

0.53

EndInit

0.51

hes

0.51

hed

0.50

 Barbados

0.49

tice

0.45

 Lanka

0.45

 Carolina

0.45

 Baptist

0.43

Còn

0.43

Activations Density 0.311%

words related to spiders and their characteristics

No Comments

No Known Activations