INDEX

Explanations

instances of the word "name."

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

事前

-0.56

 Prä

-0.52

 croy

-0.49

św

-0.47

 uyar

-0.46

 agricoles

-0.46

گوی

-0.45

 urllib

-0.44

ceros

-0.44

 lapin

-0.44

POSITIVE LOGITS

 name

0.98

المناصب

0.94

IntoConstraints

0.92

enumi

0.88

 ویکی‌پدیا

0.82

原始内容存档于

0.77

 NSCoder

0.76

 initComponents

0.76

enumii

0.74

!("{}",

0.72

Activations Density 0.162%

instances of the word "name."

No Comments

No Known Activations