INDEX

Explanations

references to bias in algorithms and their societal implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AnchorTagHelper

-0.52

cases

-0.38

 Wege

-0.37

Cyfarwyddwr

-0.37

 AppCompatTheme

-0.37

̍

-0.36



-0.35

 stadig

-0.35

ways

-0.34

 Vereinbarung

-0.33

POSITIVE LOGITS

setVerticalGroup

0.56

 quality

0.56

 kwaliteit

0.54

 Accuracy

0.51

msgTypes

0.49

 flawed

0.48

quality

0.48

 Quality

0.48

 inaccuracies

0.47

 QUALITY

0.47

Activations Density 0.514%

references to bias in algorithms and their societal implications

No Comments

No Known Activations