INDEX

Explanations

references to memorials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ViewFeatures

-0.92

Autoritní

-0.92

 myſelf

-0.85

 '\\;'

-0.83

PreferredItem

-0.82

 faſt

-0.81

 iſt

-0.81

 ―――――

-0.80

 Houſe

-0.79

 ſhall

-0.78

POSITIVE LOGITS

 Memorial

0.91

Memorial

0.70

 MEMORIAL

0.60

ical

0.58

Permit

0.52

 asper

0.52

MEMOR

0.51

symbol

0.51

х

0.50

 consulte

0.49

Activations Density 0.057%

references to memorials

No Comments

No Known Activations