INDEX

Explanations

phrases and words related to introductions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

BooleanField

-0.64

lwjgl

-0.61

 lipids

-0.58

ma

-0.57

(:,

-0.56

 Sita

-0.56

valueOf

-0.56

glu

-0.55

ISSN

-0.55

gdx

-0.54

POSITIVE LOGITS

 introduce

3.44

 Introduce

3.31

 introduced

3.25

 introduces

3.22

 introducing

3.22

 introduction

3.17

introduce

3.13

Introduce

2.95

 introductions

2.95

 Introducing

2.92

Activations Density 0.083%

phrases and words related to introductions

No Comments

No Known Activations