INDEX

Explanations

positive sentiments about features and experiences

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

arrangement gives

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 صوتيه

-0.73

出版年

-0.58

SourceChecksum

-0.51

下载附件

-0.50

OrBuilder

-0.50

enterOuterAlt

-0.49

̈́

-0.46

WebServlet

-0.44

salms

-0.43

ագրություններ

-0.42

POSITIVE LOGITS

 nice

0.41

 gesture

0.38

sin

0.37

seeing

0.36

เลย

0.36

anjutnya

0.36

genu

0.35

 genuinely

0.35

Hit

0.35

 pensées

0.35

Activations Density 0.011%

positive sentiments about features and experiences

arrangement gives

No Comments

No Known Activations