INDEX

Explanations

references to specific reports and articles, particularly news sources and associated dates

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

 otomatig

-0.49

 MyBatis

-0.49

MethodManager

-0.47

 '\\;'

-0.46

 المعيارى

-0.44

 inflater

-0.43

Vit

-0.43

addCriterion

-0.43

 Tick

-0.42

 الص

-0.42

POSITIVE LOGITS

 Infórmanos

0.47

 мәкалә

0.43

 themſelves

0.42

Lähteet

0.40

 trône

0.39

 poète

0.38

 ſche

0.38

 Monfieur

0.38

 Noviembre

0.37

 información

0.37

Activations Density 0.389%

references to specific reports and articles, particularly news sources and associated dates

No Comments

No Known Activations