INDEX

Explanations

expressions of gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 model

-0.36

 Wirt

-0.36

VersionUID

-0.35

⦁

-0.35

 cases

-0.35

 Weiden

-0.34

model

-0.34

or

-0.33

◦

-0.33

◗

-0.33

POSITIVE LOGITS

 thanks

0.98

 Thanks

0.97

 thanked

0.97

thanks

0.94

 thank

0.93

 THANKS

0.91

 thanking

0.91

 Thank

0.90

thank

0.89

 thankful

0.89

Activations Density 0.096%

expressions of gratitude

No Comments

No Known Activations

expressions of gratitude

No Comments

No Known Activations