INDEX

Explanations

terms related to energy and its various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MockBean

-0.83

Revis

-0.76

 Gothenburg

-0.76

 faulting

-0.74

améli

-0.72

__*/

-0.71

 Rump

-0.71

chtenstein

-0.69

ttemberg

-0.69

 Revis

-0.69

POSITIVE LOGITS

 energy

1.58

 energies

1.49

 Energy

1.46

ENERGY

1.44

 ENERGY

1.43

energy

1.34

Energy

1.25

energies

1.22

 Ener

1.20

Ener

1.17

Activations Density 0.058%

terms related to energy and its various contexts

No Comments

No Known Activations