INDEX

Explanations

programming-related keywords and definitions

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

Code snippets (often involving graphics or initialization)

np_acts-logits-general · gemini-2.0-flash

Point coordinates and drawing commands

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bisous

-0.59

 okuyayım

-0.58

tisseur

-0.58

 Italijani

-0.53

bonucleic

-0.53

 utafitiHapana

-0.53

 otomatig

-0.53

 RSSSF

-0.52

bisous

-0.51

 препратки

-0.51

POSITIVE LOGITS

Point

0.90

point

0.79

awtextra

0.75

 point

0.75

 Point

0.74

CGRectMake

0.70

 POINT

0.69

CodeAttribute

0.65

getPoint

0.65

InjectAttribute

0.60

Activations Density 0.004%

programming-related keywords and definitions

Code snippets (often involving graphics or initialization)

Point coordinates and drawing commands

No Comments

No Known Activations