INDEX

Explanations

code-related terms and definitions in programming contexts

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

Lines of code involving file sessions and queries

np_acts-logits-general · gemini-2.0-flash

enum or type qualifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

цията

-0.46

 Bourgoin

-0.44

gdala

-0.43

Sherlock

-0.43

EndGlobalSection

-0.43

шкан

-0.42

inheritdoc

-0.40

IMON

-0.40

toli

-0.39

Coordonnées

-0.39

POSITIVE LOGITS

 FetchType

1.29

DockStyle

1.19

FetchType

1.05

 GenerationType

0.93

GenerationType

0.92

TagMode

0.86

 Мексичка

0.84

extAlignment

0.82

AnchorStyles

0.81

SizeMode

0.78

Activations Density 0.330%

code-related terms and definitions in programming contexts

Lines of code involving file sessions and queries

enum or type qualifiers

No Comments

No Known Activations