INDEX

Explanations

terms related to coverage and protection in the context of services or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

fjspx

-1.02

tagHelperRunner

-1.02

IntoConstraints

-0.94

 المعيارى

-0.94

 disambiguazione

-0.93

-0.83

Personensuche

-0.82

HasAnnotation

-0.82

 bezeichneter

-0.81

 محفوظة

-0.81

POSITIVE LOGITS

per

1.76

per

1.20

Per

1.07

Per

1.02

 necessarily

1.00

 proprement

0.94

 itself

0.92

 specifically

0.92

 perse

0.86

 strictly

0.82

Activations Density 0.357%

terms related to coverage and protection in the context of services or products

No Comments

No Known Activations