INDEX

Explanations

phrases related to statements or actions made by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 defaultstate

-0.59

CloseOperation

-0.56

 useRouter

-0.55

PathVariable

-0.54

 BoxDecoration

-0.47

testens

-0.47

flashdata

-0.46

 CommonModule

-0.46

yarnpkg

-0.46

addGap

-0.46

POSITIVE LOGITS

My

3.88

My

3.68

MY

2.85

my

2.74

MY

2.70

my

2.51

getMy

2.26

 Mijn

2.06

 Мой

2.06

 我的

2.01

Activations Density 0.519%

phrases related to statements or actions made by individuals

No Comments

No Known Activations