INDEX

Explanations

question and answer formats in text

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

questions starting with what

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 BoxFit

-0.88

 MainAxisSize

-0.70

AnchorTagHelper

-0.68

ModelSerializer

-0.67

UrlResolution

-0.66

 estekak

-0.65

OGND

-0.65

bardier

-0.64

存于互联网档案馆

-0.63

 Autorizaciones

-0.60

POSITIVE LOGITS

 describe

0.38

why

0.36

 composição

0.35

 composición

0.35

 deose

0.34

 first

0.33

 composizione

0.32

 explain

0.32

 mengapa

0.32

Why

0.32

Activations Density 0.003%

question and answer formats in text

questions starting with what

No Comments

No Known Activations