INDEX

Explanations

references to nuclear weapons and their related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 houden

-0.52

loger

-0.48

支持

-0.45

Trama

-0.45

其

-0.45

 fournies

-0.44

 dissipate

-0.44

-0.43

 اثر

-0.43

 Este

-0.42

POSITIVE LOGITS

########.

1.02

CloseOperation

1.00

RenderAtEndOf

0.91

Tembelea

0.90

BeginContext

0.88

 виправивши

0.88

twimg

0.87

makeConstraints

0.83

 houſe

0.80

SBATCH

0.80

Activations Density 2.046%

references to nuclear weapons and their related concepts

No Comments

No Known Activations

references to nuclear weapons and their related concepts

No Comments

No Known Activations