INDEX

Explanations

terms and phrases related to criteria and standards

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Shand

-0.73

 Beauchamp

-0.69

Bounding

-0.69

Chham

-0.69

tvguidetime

-0.69

𝘨

-0.69

Pent

-0.68

balanceOf

-0.67

Wins

-0.67

++]=

-0.66

POSITIVE LOGITS

 criteria

2.19

 Criteria

1.98

criteria

1.94

 CRITERIA

1.83

Criteria

1.77

 criterion

1.55

 Criterion

1.36

 criter

1.35

 critères

1.26

riteria

1.19

Activations Density 0.095%

terms and phrases related to criteria and standards

No Comments

No Known Activations