INDEX

Explanations

terms related to "world" and its various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 للاسماء

-0.89

 Ryanair

-0.82

Xie

-0.82

 desta

-0.80

 Notary

-0.77

Amos

-0.76

 Mortar

-0.74

 Tattoos

-0.74

 Amtrak

-0.74

 Knudsen

-0.73

POSITIVE LOGITS

 World

1.58

 world

1.56

 WORLD

1.49

World

1.36

world

1.33

WORLD

1.31

 Worlds

1.29

 worlds

1.27

worlds

1.26

Worlds

1.23

Activations Density 0.051%

terms related to "world" and its various contexts

No Comments

No Known Activations