INDEX

Explanations

references to inclusivity or collective terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 apprécier

-0.42

プリング

-0.42

 discorso

-0.42

SequentialGroup

-0.41

 sécurisé

-0.41

 digitais

-0.40

 decirle

-0.40

 toimi

-0.40

 gewisser

-0.39

 independientes

-0.38

POSITIVE LOGITS

 todos

2.17

 tous

2.08

 tutti

1.98

 Todos

1.95

Todos

1.88

 TODOS

1.76

 Tous

1.72

 Tutti

1.68

Tous

1.66

Tutti

1.63

Activations Density 0.074%

references to inclusivity or collective terms

No Comments

No Known Activations