INDEX

Explanations

terms related to rewards and punishments

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

concepts related to rewards, recognition, and outcomes of actions.

oai_token-act-pair · gpt-4o Triggered by @timna

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.*")]

-0.65

 препратки

-0.62

WebRequest

-0.62

Enlaces

-0.58

 Larkin

-0.57

 surla

-0.57

ьа

-0.56

Fle

-0.56

 CGRect

-0.55

Vat

-0.55

POSITIVE LOGITS

 reward

1.73

 rewards

1.59

 Reward

1.52

reward

1.44

 Rewards

1.42

Reward

1.39

 rewarded

1.37

Rewards

1.26

 rewarding

1.23

 punish

1.19

Activations Density 0.144%

terms related to rewards and punishments

concepts related to rewards, recognition, and outcomes of actions.

No Comments

No Known Activations