INDEX

Explanations

mathematical symbols and notations related to formal proofs and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

abstractmethod

-0.62

-0.56

CppMethod

-0.52

stateMutability

-0.52

lasz

-0.51

gye

-0.46

 inter

-0.46

 activity

-0.43

пре

-0.43

icc

-0.43

POSITIVE LOGITS

 ligiloj

0.80

 myſelf

0.76

 تانيه

0.76

 itſelf

0.75

 purpoſe

0.75

ContentAlignment

0.73

 greateſt

0.72

 ſtand

0.70

 ſmall

0.69

 whoſe

0.68

Activations Density 1.902%

mathematical symbols and notations related to formal proofs and definitions

No Comments

No Known Activations