INDEX

Explanations

future predictions or intentions regarding publishing content

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

sizeCache

-0.67

SharedCtor

-0.64

lapsingToolbar

-0.62

buttonBar

-0.59

 mapStateToProps

-0.56

AsUp

-0.55

PhysRevLett

-0.55

########.

-0.53

省市镇

-0.51

 cdti

-0.50

POSITIVE LOGITS

 blog

0.64

 posts

0.57

 pretty

0.57

AddTagHelper

0.56

 đứa

0.54

 awhile

0.53

my

0.52

 ramb

0.51

 stuff

0.51

 posting

0.51

Activations Density 0.427%

future predictions or intentions regarding publishing content

No Comments

No Known Activations