INDEX

Explanations

expressions of enjoyment or positive feedback related to experiences or products

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

CloseOperation

-0.64

EndContext

-0.62

 smtplib

-0.58

 Biôgrafia

-0.52

 oprot

-0.49

 كومونز

-0.49

 Wikimedijinoj

-0.48

Slf

-0.47

extAlignment

-0.46

 MainAxisSize

-0.44

POSITIVE LOGITS

 praise

0.63

 praised

0.62

 evaluation

0.57

 critique

0.56

 impressed

0.56

 praising

0.56

:✨

0.54

 praises

0.53

 appreciation

0.53

 critiques

0.52

Activations Density 0.438%

expressions of enjoyment or positive feedback related to experiences or products

No Comments

No Known Activations