INDEX

Explanations

terms related to legal charges and accusations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Мексичка

-0.86

theless

-0.86

 bint

-0.85

 Alley

-0.84

 poppies

-0.83

 Romain

-0.83

🙃

-0.83

ゞ

-0.83

 albedo

-0.82

\"");

-0.81

POSITIVE LOGITS

 charge

2.34

 charges

2.31

charge

2.19

 Charge

2.15

Charge

2.11

 Charges

2.04

charges

2.03

 charged

2.00

 CHARGE

1.96

Charges

1.92

Activations Density 0.060%

terms related to legal charges and accusations

No Comments

No Known Activations