INDEX

Explanations

references to bonuses or incentives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 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

 Chriftian

-0.45

 jugement

-0.44

 gouver

-0.43

 poffible

-0.41

NewReader

-0.40

 passagers

-0.40

 cristian

-0.39

 judgement

-0.38

 Menschheit

-0.38

 Judgment

-0.38

POSITIVE LOGITS

 enjoys

0.74

 thrive

0.73

 Bonus

0.70

 thrives

0.70

 thriving

0.68

 thrived

0.66

 enjoy

0.65

bonus

0.64

.*")]

0.64

 bonus

0.62

Activations Density 0.264%

references to bonuses or incentives

No Comments

No Known Activations