INDEX

Explanations

mentions of things being open or opening

oai_token-act-pair · gemini-2.0-flash

instances of the word 'open'

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

open

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

RegressionTest

-0.73

CWE

-0.65

[]*

-0.63

aktery

-0.61

tude

-0.58

 CURIAM

-0.57

andoah

-0.56

extAlignment

-0.56

 kaynağından

-0.55

KommentareTeilen

-0.55

POSITIVE LOGITS

Gön

0.52

shortcuts

0.45

 recev

0.44

 defaultstate

0.44

 مرئيه

0.44

 الاطلاع

0.42

 braccia

0.40

 accett

0.40

 AssemblyCulture

0.40

May

0.39

Activations Density 1.610%

mentions of things being open or opening

instances of the word 'open'

open

No Comments

No Known Activations