INDEX

Explanations

dots in various contexts, typically indicating method calls or property access in a programming context

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

accessing object attributes or methods

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

 Brou

-0.41

<eos>

-0.38

 rocz

-0.38

 intptr

-0.38

SequentialGroup

-0.36

 Absch

-0.35

occasione

-0.35

 Réponses

-0.34

 lembrar

-0.34

 promoção

-0.34

POSITIVE LOGITS

 createState

0.58

IContainer

0.58

moiselle

0.53

OGND

0.49

matchCondition

0.48

 picioare

0.46

Fordítás

0.46

 internal

0.46

adaptiveStyles

0.45

XmlAccessType

0.45

Activations Density 0.048%

dots in various contexts, typically indicating method calls or property access in a programming context

accessing object attributes or methods

No Comments

No Known Activations