INDEX

Explanations

terms related to framing and print sizing

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

⅘

-0.36

 confirmations

-0.36

Appearances

-0.35

外観

-0.34

kubernetes

-0.34

 detalla

-0.34

 Liter

-0.34

cipes

-0.34

başı

-0.34

 devol

-0.34

POSITIVE LOGITS

 صوتيه

0.63

WebServlet

0.60

SourceChecksum

0.56

 betweenstory

0.55

 ویکی‌پدی

0.54

IndentedString

0.54

 enmar

0.52

JoinTable

0.52

URLException

0.50

MemoryWarning

0.48

Activations Density 0.330%

terms related to framing and print sizing

No Comments

No Known Activations