INDEX

Explanations

elements of code or programming constructs related to user interface controls

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

Code snippets or code-like text

np_acts-logits-general · gemini-2.0-flash

ia* Linear

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aarrggbb

-0.69

GEBURTSDATUM

-0.65

DeleteBehavior

-0.65

RTEE

-0.62

rungsseite

-0.61

 StatefulWidget

-0.60

SharedDtor

-0.60

matchCondition

-0.60

onOptions

-0.59

 Familienname

-0.57

POSITIVE LOGITS

 covered

0.67

covered

0.62

 Covered

0.61

Covered

0.51

 licked

0.50

☸

0.48

 Govern

0.47

 volum

0.47

SequentialGroup

0.46

 Coverage

0.46

Activations Density 0.029%

elements of code or programming constructs related to user interface controls

Code snippets or code-like text

ia* Linear

No Comments

No Known Activations