INDEX

Explanations

names and references to specific legal cases or entities

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

 religieuses

-0.87

 ainfi

-0.86

 estekak

-0.83

 avoient

-0.82

 étoient

-0.81

 présidenti

-0.81

 pinulongan

-0.81

 déliv

-0.79

 connue

-0.79

rungsseite

-0.78

POSITIVE LOGITS

0.76

 experience

0.73

0.72

 example

0.71

 program

0.71

 piece

0.70

 application

0.70

 brand

0.69

 team

0.67

 post

0.67

Activations Density 0.776%

names and references to specific legal cases or entities

No Comments

No Known Activations