INDEX

Explanations

occurrences of return statements in code

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

return statement

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

GEBURTSDATUM

-1.38

Personensuche

-1.03

 disambiguazione

-1.02

Personendaten

-1.00

 queſta

-0.89

 autorytatywna

-0.88

 незавершена

-0.88

SequentialGroup

-0.88

featureID

-0.87

parsedMessage

-0.86

POSITIVE LOGITS

 again

0.44

 likewise

0.40

 ebenfalls

0.36

а

0.35

0.32

for

0.32

↵

0.32

 safe

0.32

0.30

 Again

0.30

Activations Density 0.003%

occurrences of return statements in code

return statement

No Comments

No Known Activations