INDEX

Explanations

phrases that indicate an increase or elevation in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

最快更新

-0.48

Sna

-0.44

 missing

-0.42

 clean

-0.42

 bị

-0.41

нимание

-0.41

jface

-0.41

re

-0.40

 сожалению

-0.40

POSITIVE LOGITS

AddTagHelper

1.20

ValueStyle

1.16

ChildScrollView

0.88

Datuak

0.87

DockStyle

0.83

SequentialGroup

0.80

 الرياضيه

0.78

makeConstraints

0.78

RTGC

0.78

 Referential

0.77

Activations Density 0.526%

phrases that indicate an increase or elevation in context

No Comments

No Known Activations