INDEX

Explanations

phrases that indicate relationships or connections between concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 réguli

-0.47

 tanpa

-0.46

Lähteet

-0.44

 output

-0.44

divarius

-0.44

 powerful

-0.44

 vær

-0.44

 most

-0.43

 without

-0.43

kå

-0.43

POSITIVE LOGITS

 متعلقه

1.26

 relating

1.24

 pertain

1.22

 pertaining

1.20

 pertains

1.18

 '\\;'

1.11

 concerning

1.07

Concerning

1.03

 regarding

1.02

 Concerning

1.02

Activations Density 0.351%

phrases that indicate relationships or connections between concepts

No Comments

No Known Activations