INDEX

Explanations

references to legal charges and responsibilities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Chriftian

-0.92

DockStyle

-0.91

 myſelf

-0.88

 Majefty

-0.88

 مشين

-0.84

 himſelf

-0.84

 Jefus

-0.84

ViewFeatures

-0.82

 autorytatywna

-0.81

 Chrif

-0.81

POSITIVE LOGITS

 charge

1.10

charge

0.93

 Charge

0.81

 charges

0.79

CHARGE

0.77

 CHARGE

0.76

Charge

0.74

charges

0.69

Gre

0.66

át

0.65

Activations Density 0.051%

references to legal charges and responsibilities

No Known Activations