INDEX

Explanations

references to the Army and related military terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.69

 Folsom

-0.68

-0.67

SWG

-0.66

gnore

-0.65

}^{*}(

-0.64

 anything

-0.64

zkod

-0.63

 Với

-0.63

bic

-0.63

POSITIVE LOGITS

SBATCH

0.91

DockStyle

0.90

mybatisplus

0.86

eba

0.86

teries

0.84

mtable

0.83

 Spartans

0.81

maries

0.80

nterior

0.80

CMR

0.80

Activations Density 0.087%

references to the Army and related military terms

No Comments

No Known Activations