INDEX

Explanations

references to tips or advisory phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 Sabina

-0.62

itects

-0.59

CodedInputStream

-0.59

 Guer

-0.59

--}}

-0.59

клопе

-0.58

*/

-0.58

]$}

-0.58

cist

-0.57

 }}$}

-0.56

POSITIVE LOGITS

tip

1.53

Tip

1.48

Tip

1.39

 tips

1.38

 Tips

1.35

TIP

1.34

tip

1.32

TIP

1.25

Tips

1.23

tips

1.13

Activations Density 0.075%

references to tips or advisory phrases

No Comments

No Known Activations