INDEX

Explanations

elements related to predictive modeling and evaluation of significant factors in research contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.86

 Monfieur

-0.72

 图解

-0.71

∎

-0.71

Yud

-0.70

iastes

-0.69

 <<<<<<<<<<<<<<

-0.69

 Aten

-0.69

 estekak

-0.69

ItemBackground

-0.68

POSITIVE LOGITS

就

1.18

就

0.98

他就

0.94

她就

0.90

我就

0.87

的就

0.81

都

0.80

便

0.78

你就

0.76

那就

0.76

Activations Density 0.034%

elements related to predictive modeling and evaluation of significant factors in research contexts

No Comments

No Known Activations