INDEX

Explanations

phrases related to hypotheses and expected outcomes in scientific research

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

preceding "expected" or similar

np_acts-logits-general · gemini-2.0-flash

expectations and predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

EndInit

-0.46

featureID

-0.44

 Roskov

-0.43

 ujednoznacz

-0.43

 transfieras

-0.40

endwhile

-0.39

AddTagHelper

-0.39

oredCriteria

-0.38

 kasarigan

-0.37

Ɓ

-0.37

POSITIVE LOGITS

 expected

2.36

 expect

2.22

 Expect

2.06

expected

2.02

 Expected

2.00

 expects

1.99

 EXPECT

1.99

Expect

1.95

expect

1.91

Expected

1.91

Activations Density 0.659%

phrases related to hypotheses and expected outcomes in scientific research

preceding "expected" or similar

expectations and predictions

No Comments

No Known Activations