INDEX

Explanations

mentions of separation or division

oai_token-act-pair · gemini-2.0-flash

contexts involving separation or division

np_token-act-pair-logits · gpt-4o-mini

Splitting

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dymyr

-0.66

 يتيمه

-0.61

 <<<<<<<<<<<<<<

-0.54

endphp

-0.54

celes

-0.53

invokeLater

-0.52

 disambiguazione

-0.51

#+#

-0.50

سطس

-0.49

WebVitals

-0.49

POSITIVE LOGITS

 open

0.87

 apart

0.81

open

0.78

apart

0.71

Open

0.71

 abierta

0.67

 ouverte

0.65

 Open

0.64

 abierto

0.64

OPEN

0.61

Activations Density 1.469%

mentions of separation or division

contexts involving separation or division

Splitting

No Comments

No Known Activations