INDEX

Explanations

references to personal identity and cultural commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

出版年

-0.55

disposing

-0.54

Origen

-0.49

://

-0.49

Item

-0.48

δι

-0.47

 itens

-0.46

accio

-0.46

Pro

-0.45

 NUKAT

-0.45

POSITIVE LOGITS

OrBuilder

0.68

endom

0.65

EDEFAULT

0.63

IndentedString

0.63

ۜ

0.59

 newBuilder

0.58

+:+

0.58

 дописавши

0.57

Сылтамалар

0.56

 estimés

0.56

Activations Density 0.213%

references to personal identity and cultural commentary

No Comments

No Known Activations