INDEX

Explanations

terms related to legal appeals and processes

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

osh

-0.67

-0.66

-0.63

odly

-0.62

 Schroeder

-0.62

PropertyChanging

-0.61

-0.60

Jeografia

-0.60

masta

-0.60

alina

-0.59

POSITIVE LOGITS

 appeal

2.15

 Appeal

2.14

 APPEAL

2.07

appeal

1.98

Appeal

1.97

 appeals

1.93

 appealed

1.93

 Appeals

1.87

Appe

1.84

 appealing

1.73

Activations Density 0.146%

terms related to legal appeals and processes

No Comments

No Known Activations