INDEX

Explanations

phrases related to checking for updates or news

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

EndContext

-0.68

 AttributeSet

-0.64

TargetException

-0.59

GenerationType

-0.59

BeginInit

-0.58

<?

-0.58

tagHelper

-0.58

 समीक्षाएं

-0.58

__;

-0.58

specialchars

-0.58

POSITIVE LOGITS

 monitoring

0.63

 monitor

0.60

 updates

0.59

updates

0.56

 monitors

0.55

 monitored

0.55

antikan

0.54

 мони

0.53

monitoring

0.53

 takip

0.53

Activations Density 0.212%

phrases related to checking for updates or news

No Comments

No Known Activations