INDEX

Explanations

words that frequently occur in code

oai_token-act-pair · gemini-2.0-flash

Code

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

trường

-0.56

Investment

-0.54

employeeId

-0.52

Accounting

-0.51

Organizations

-0.50

Applicant

-0.50

Municip

-0.50

Organizational

-0.49

Inquiry

-0.48

Participation

-0.48

POSITIVE LOGITS

StructEnd

0.88

 defaultstate

0.88

 فريبيس

0.86

WriteBarrier

0.76

DockStyle

0.73

:✨

0.73

PerformLayout

0.73

StoryboardSegue

0.70

addCriterion

0.68

complexContent

0.68

Activations Density 8.388%

words that frequently occur in code

Code

No Comments

No Known Activations