INDEX

Explanations

programming-related terminology and structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

In Swift or Dart code

np_acts-logits-general · gemini-2.0-flash

programming keywords

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adə

-0.61

 varargin

-0.56

 bőr

-0.53

\{\\

-0.53

featureID

-0.52

İyi

-0.49

onesa

-0.49

 udaler

-0.49

 HttpServlet

-0.48

imetric

-0.48

POSITIVE LOGITS

dart

0.76

("${

0.70

flutter

0.67

 flutter

0.62

'${

0.61

 Flutter

0.61

Future

0.60

 StatefulWidget

0.60

widget

0.60

Dart

0.60

Activations Density 0.122%

programming-related terminology and structures

In Swift or Dart code

programming keywords

No Comments

No Known Activations