INDEX

Explanations

references to crowns, both in a literal and metaphorical sense

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 FetchType

-0.49

Хьажоргаш

-0.49

IUrlHelper

-0.46

BufferException

-0.45

忌

-0.43

naio

-0.43

Joc

-0.43

Paco

-0.43

 Jeans

-0.42

parsedMessage

-0.42

POSITIVE LOGITS

 crown

2.17

 Crown

2.02

Crown

1.98

crown

1.88

 CROWN

1.87

 crowns

1.76

 Crowns

1.55

 crowned

1.52

 coroa

1.52

 couronne

1.45

Activations Density 0.193%

references to crowns, both in a literal and metaphorical sense

No Comments

No Known Activations