INDEX

Explanations

references to harm or risk associated with actions or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 viață

-0.48

 cementerio

-0.48

 cesse

-0.48

JMenuBar

-0.46

ẢN

-0.46

 Varian

-0.45

 gelassen

-0.45

,:);

-0.45

깥

-0.44

رسال

-0.43

POSITIVE LOGITS

 harmed

1.03

 harming

0.97

 harm

0.93

 harms

0.92

harmed

0.88

 hurting

0.87

脚注の使い方

0.87

 Harm

0.85

harm

0.85

 hurt

0.82

Activations Density 0.347%

references to harm or risk associated with actions or situations

No Comments

No Known Activations