INDEX

Explanations

expectation-related terms and phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

SBATCH

-0.83

 librement

-0.81

 avoient

-0.81

ulho

-0.78

 étoient

-0.74

\{\\

-0.74

 hindurch

-0.74

 doucement

-0.72

 niega

-0.72

(!__

-0.71

POSITIVE LOGITS

 expected

1.37

 Expected

1.35

Expected

1.30

expected

1.29

 EXPECT

0.99

EXPECTED

0.98

 expectations

0.98

 expectation

0.95

 anticipated

0.93

Expectations

0.88

Activations Density 0.070%

expectation-related terms and phrases

No Comments

No Known Activations