INDEX

Explanations

references to items in a list or collection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

GraphicsUnit

-0.94

SaveChanges

-0.94

 Reſ

-0.88

 تضيفلها

-0.84

 whoſe

-0.81

 Conſ

-0.80

Eſ

-0.80

 '\\;'

-0.80

 raiſ

-0.79

 Maury

-0.79

POSITIVE LOGITS

Item

1.57

 Item

1.52

 ITEM

1.50

ITEM

1.39

 item

1.30

item

1.20

setItem

1.12

 getItem

1.08

titem

1.06

ItemBackground

1.06

Activations Density 0.044%

references to items in a list or collection

No Comments

No Known Activations