INDEX

Explanations

phrases related to legal judgments and adjustments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

:✨

-0.63

 uſed

-0.56

ſelf

-0.55

InjectAttribute

-0.54

 ſtre

-0.54

 Perſ

-0.54

 Chriftian

-0.53

 inſ

-0.52

 ſhould

-0.51

 preſ

-0.51

POSITIVE LOGITS

 accordingly

2.34

 correspondingly

1.85

 Accordingly

1.67

Accordingly

1.59

 conséquence

1.39

 entsprechend

1.28

 consequently

1.28

 соответственно

1.27

 corresponding

1.24

 conseguenza

1.23

Activations Density 0.389%

phrases related to legal judgments and adjustments

No Comments

No Known Activations