INDEX

Explanations

references to insurance and related terms

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

Viitteet

-0.91

 joindre

-0.84

 getRule

-0.81

+#+#

-0.76

DispatchToProps

-0.75

 setOpen

-0.74

orteur

-0.73

 cardíaca

-0.73

umumkan

-0.72

.*")]

-0.72

POSITIVE LOGITS

 loan

0.85

 insurance

0.79

 loans

0.73

 pension

0.71

<eos>

0.67

 miras

0.66

 taba

0.66

 Insurance

0.66

 Clinton

0.66

ioni

0.65

Activations Density 0.069%

references to insurance and related terms

No Comments

No Known Activations