INDEX

Explanations

concluding remarks or sections in documents

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-1.17

 itſelf

-1.09

 pleaſure

-1.02

 Monfieur

-1.02

 purpoſe

-1.00

Efq

-0.97

 himſelf

-0.94

ſelves

-0.94

 houſe

-0.93

 Anſ

-0.93

POSITIVE LOGITS

<eos>

0.70

 Finally

0.58

 conclure

0.56

 finally

0.55

Finally

0.55

 final

0.51

finally

0.48

astify

0.48

 infine

0.46

Conclusion

0.46

Activations Density 0.413%

concluding remarks or sections in documents

No Comments

No Known Activations