INDEX

Explanations

key attributes and qualities associated with products and concepts in health, therapy, and technology

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

our daily lives

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

 snippetHide

-0.63

Personendaten

-0.50

BufferException

-0.48

RegressionTest

-0.48



-0.47

 referrerpolicy

-0.46

prepareStatement

-0.46

mbggenerated

-0.46

#+#

-0.45

inSlope

-0.45

POSITIVE LOGITS

our

0.38

がございます

0.38

 noqa

0.37

 informée

0.35

 alak

0.34

是我们

0.33

 úč

0.33

 your

0.33

 dormitórios

0.33

our

0.33

Activations Density 0.023%

key attributes and qualities associated with products and concepts in health, therapy, and technology

our daily lives

No Comments

No Known Activations