INDEX

Explanations

clauses that express intent, obligation, or possibility by using "to" with a verb or the auxiliary verbs "will", "would", "should", "can", "may" or "must".

oai_token-act-pair · gemini-2.0-flash

to

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

tagHelperRunner

-0.95

GenerationType

-0.67

AddHtmlAttribute

-0.66

verwijspagina

-0.66

EndProject

-0.65

Geplaatst

-0.65

EndContext

-0.64

 AssemblyTitle

-0.63

abestanden

-0.63

LookAnd

-0.62

POSITIVE LOGITS

lay

0.76

 hand

0.62

lay

0.59

Lay

0.58

Lay

0.55

HAND

0.54

 press

0.52

 grant

0.52

LAY

0.51

hand

0.50

Activations Density 4.655%

clauses that express intent, obligation, or possibility by using "to" with a verb or the auxiliary verbs "will", "would", "should", "can", "may" or "must".

to

No Comments

No Known Activations