INDEX

Explanations

words related to actions and behavior, particularly how people interact with the world and others.

oai_token-act-pair · gemini-2.0-flash

Situations and behavior

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rawDesc

-0.48

COURT

-0.47

NSIndexPath

-0.45

XmlAccessType

-0.44

atoday

-0.44

 Court

-0.43

 întâ

-0.43

 Schell

-0.42

 Centrale

-0.42

 évit

-0.42

POSITIVE LOGITS

цездатний

0.86

oredCriteria

0.77

IUrlHelper

0.72

IndentedString

0.71

PreferredItem

0.69

 himo

0.69

:✨

0.68

 mxArray

0.65

 kasarigan

0.65

 EconPapers

0.64

Activations Density 2.213%

words related to actions and behavior, particularly how people interact with the world and others.

Situations and behavior

No Comments

No Known Activations