INDEX

Explanations

legal terms and references to previous statements or sections in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

IUrlHelper

-0.63

Efq

-0.63

 pourtant

-0.59

elock

-0.58

\{\\

-0.56

ividual

-0.56

ंदीखरीदारी

-0.56

troppo

-0.56

LookAnd

-0.55

Хьажоргаш

-0.55

POSITIVE LOGITS

 called

0.81

called

0.76

 llamado

0.70

 Called

0.69

 appelé

0.68

 appelés

0.67

pyplot

0.66

 CALLED

0.65

referred

0.65

hereinafter

0.65

Activations Density 0.378%

legal terms and references to previous statements or sections in texts

No Comments

No Known Activations