INDEX

Explanations

references to various energy levels and formats in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 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

ﬄ

-0.60

kring

-0.60

__":

-0.60

InitStruct

-0.59

__':

-0.59

gameserver

-0.58

ernoo

-0.58

Personensuche

-0.58

ONAUT

-0.58

っこう

-0.58

POSITIVE LOGITS

2.81

2.65

getE

1.62

Ｅ

1.34

𝐸

1.24

dE

1.19

cE

1.17

Е

1.14

Е

1.08

dE

1.05

Activations Density 0.120%

references to various energy levels and formats in scientific contexts

No Comments

No Known Activations

references to various energy levels and formats in scientific contexts

No Comments

No Known Activations