INDEX

Explanations

emotional expressions and reactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

rungsseite

-0.57

 Exacts

-0.46

 surla

-0.44

 Exactos

-0.44

########.

-0.43

transQ

-0.42

 referenties

-0.41

Personendaten

-0.40

 Provided

-0.40

 informée

-0.39

POSITIVE LOGITS

:(

1.48

:-(

1.36

:'(

1.22

:(

1.19

 😔

1.18

:-(

1.16

 😢

1.14

🙁

1.10

:/

1.09

;(

1.08

Activations Density 0.360%

emotional expressions and reactions

No Comments

No Known Activations