INDEX

Explanations

phrases and terms related to access dates and citations

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

ాయి

-0.47

 vốn

-0.46

-0.45

Hop

-0.45

RemoveAll

-0.45

-0.44

ciach

-0.44

Bi

-0.44

comparable

-0.44

ouw

-0.42

POSITIVE LOGITS

consulté

1.67

 consultato

1.38

 Процитовано

1.35

 Consultado

1.28

Hozzáférés

1.27

 оригіналу

1.23

Geplaatst

1.22

 abgerufen

1.17

原始内容存档于

1.15

 Abgerufen

1.09

Activations Density 0.018%

phrases and terms related to access dates and citations

No Comments

No Known Activations