INDEX

Explanations

notable literary references and quotations

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

citations and quotes

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

 informaciones

-0.54

 mentiras

-0.49

 demonios

-0.48

 bienes

-0.47

 normalidad

-0.47

 conocimientos

-0.47

 entendido

-0.46

 informado

-0.45

 lisäksi

-0.45

 capacidades

-0.45

POSITIVE LOGITS

="@+

0.64

期刊论文

0.58

 prer

0.54

"]();

0.53

+#+

0.53

 ModelExpression

0.52

ContentAsync

0.52

:+:

0.52

 Starship

0.52

 Analog

0.51

Activations Density 0.029%

notable literary references and quotations

citations and quotes

No Comments

No Known Activations