INDEX

Explanations

elements of structured data and attributes related to programming

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

code object members

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Golden

-0.45

ietf

-0.41

Demand

-0.40

Wild

-0.38

 Golden

-0.36

You

-0.35

Poor

-0.35

Suppose

-0.35

Grand

-0.34

Julius

-0.34

POSITIVE LOGITS

SourceChecksum

0.70

DockStyle

0.69

SharedDtor

0.68

SharedCtor

0.63

 intStringLen

0.60

Personensuche

0.59

sizeCache

0.58

OGND

0.57

:✨

0.56

\{\\

0.55

Activations Density 0.089%

elements of structured data and attributes related to programming

code object members

No Comments

No Known Activations