INDEX

Explanations

conditions and incentives related to rewards and exchanges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 distanciation

-0.55

Capacidad

-0.52

IContainer

-0.52

зулта

-0.48

 SEDS

-0.47

capable

-0.46

epic

-0.45

usse

-0.45

μως

-0.44

ficult

-0.44

POSITIVE LOGITS

 reward

1.00

 rewards

0.89

 rewarded

0.88

reward

0.79

Reward

0.71

 recompensa

0.71

rewards

0.70

 Reward

0.67

expandindo

0.65

 Rewards

0.64

Activations Density 0.352%

conditions and incentives related to rewards and exchanges

No Comments

No Known Activations