INDEX

Explanations

terms related to bonuses and rewards in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

squ

-0.67

rfloor

-0.65

ymce

-0.62

Squ

-0.62

uyasha

-0.62

 fears

-0.61

 LayoutInflater

-0.60

ztály

-0.59

typen

-0.59

cestors

-0.59

POSITIVE LOGITS

 bonuses

1.73

 bonus

1.73

 Bonus

1.62

 reward

1.60

 Bonuses

1.58

bonus

1.55

 rewards

1.53

Bonus

1.52

Bonuses

1.49

 BONUS

1.43

Activations Density 0.084%

terms related to bonuses and rewards in various contexts

No Comments

No Known Activations