INDEX

Explanations

sentences that describe something using forms of "to be"

oai_token-act-pair · gemini-2.0-flash

known

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

脚注の使い方

-0.69

SequentialGroup

-0.63

VersionUID

-0.57

skjaer

-0.56

dotenv

-0.48

 affitto

-0.48

DNEY

-0.47

irability

-0.47

 distanciation

-0.47

tagHelperRunner

-0.47

POSITIVE LOGITS

 known

2.81

known

2.42

 Known

2.33

Known

2.23

 KNOWN

2.13

 know

2.05

know

1.75

Know

1.72

 conocida

1.68

 Know

1.66

Activations Density 3.619%

sentences that describe something using forms of "to be"

known

No Comments

No Known Activations