INDEX

Explanations

elements related to blog functionality and user interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

SourceChecksum

-0.70

ReusableCell

-0.65

 mapStateToProps

-0.56

 resourceCulture

-0.56

fromnode

-0.55

Referències

-0.54

ExtendWith

-0.53

 NUKAT

-0.53

 indígen

-0.52

 saveiro

-0.51

POSITIVE LOGITS

 unread

0.40

 summary

0.37

 subscribed

0.36

angelog

0.35

 acord

0.35



0.35

 neutral

0.34

 summar

0.34

 filter

0.33

 filtered

0.33

Activations Density 0.466%

elements related to blog functionality and user interaction

No Comments

No Known Activations