INDEX

Explanations

comments expressing user feedback or suggestions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

Rüyada

-0.47

Moreover

-0.47

transQ

-0.45

Furthermore

-0.43

このように

-0.43

 himſelf

-0.42

あるいは

-0.40

 Moreover

-0.39

 Furthermore

-0.39

のである

-0.39

POSITIVE LOGITS

 Been

1.30

Been

1.27

 Seems

1.10

 Didn

1.03

 Gonna

1.02

 haven

1.02

 been

1.02

Got

1.01

got

1.00

 Looks

1.00

Activations Density 0.801%

comments expressing user feedback or suggestions

No Comments

No Known Activations

comments expressing user feedback or suggestions

No Comments

No Known Activations