INDEX

Explanations

expletives and derogatory terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

marginVertical

-0.60

AxisAlignment

-0.60

LinkId

-0.57

stateProvider

-0.57

awtextra

-0.55

OneToMany

-0.55

 ExecuteAsync

-0.54

GOTREF

-0.51

ண்டும்

-0.48

ieuses

-0.48

POSITIVE LOGITS

 outta

0.73

hole

0.71

RegressionTest

0.69

 depositphotos

0.68

holes

0.63

face

0.62

HOLE

0.61

 pngtree

0.60

 Majefty

0.60

 gettyimages

0.60

Activations Density 0.149%

expletives and derogatory terms

No Comments

No Known Activations