INDEX

Explanations

language that suggests helpful behavior, like how to cope with a problem or how to do a task effectively

oai_token-act-pair · gemini-2.0-flash

some

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

addCriterion

-0.53

กัน

-0.50

ندران

-0.47

qu

-0.46

 interesar

-0.43

 lộc

-0.42

Sequence

-0.42

Personensuche

-0.42

orteur

-0.41

cèse

-0.41

POSITIVE LOGITS

migrationBuilder

0.98

TagHelper

0.72

 MainAxisSize

0.68

 EconPapers

0.65

IMPORTED

0.63

 typelib

0.60

///</

0.60

ArrowToggle

0.59

 parseFrom

0.59

onActivityResult

0.59

Activations Density 4.205%

language that suggests helpful behavior, like how to cope with a problem or how to do a task effectively

some

No Comments

No Known Activations