INDEX

Explanations

information related to facilities and their capacities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Quality

-0.43

imple

-0.43

 quality

-0.42

LIBR

-0.42

交

-0.41

tring

-0.39

Sidenav

-0.39

quality

-0.39

 volunt

-0.39

 missp

-0.38

POSITIVE LOGITS

 capacity

1.58

 Capacity

1.45

capacity

1.42

Capacity

1.33

 capacities

1.33

 CAPACITY

1.23

 seats

1.20

CAPACITY

1.19

 seating

1.18

 capacidad

1.17

Activations Density 0.101%

information related to facilities and their capacities

No Comments

No Known Activations