INDEX

Explanations

representations of data related to computing and processing units

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

 nakalista

-0.82

mals

-0.81

 dring

-0.78

ting

-0.76

 contextLoads

-0.73

ring

-0.72

 Malk

-0.72

cet

-0.72

 Bord

-0.71

yszcz

-0.71

POSITIVE LOGITS

1.03

uzu

0.92

 McQu

0.92

uuuu

0.91

VU

0.90

VU

0.89

 McGu

0.88

Sku

0.88

hu

0.87

CFU

0.87

Activations Density 0.344%

representations of data related to computing and processing units

No Comments

No Known Activations