INDEX

Explanations

terms related to eligibility and qualifications for programs or benefits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 empre

-0.79

 Clos

-0.76

'/',

-0.74

Guan

-0.72

 gainera

-0.71

 Crusader

-0.68

+#+

-0.68

clos

-0.67

 {}));

-0.67

 Guan

-0.66

POSITIVE LOGITS

 eligible

1.61

eligible

1.47

Eligible

1.46

 Eligible

1.39

 Eligibility

1.28

 eligibility

1.27

Eligibility

1.14

 ineligible

1.12

entitled

1.01

 entitled

1.00

Activations Density 0.100%

terms related to eligibility and qualifications for programs or benefits

No Comments

No Known Activations