INDEX

Explanations

references to personal experiences and inquiries

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 surla

-0.59

DockStyle

-0.52

scribers

-0.48

 informée

-0.48

__*/

-0.47

省市镇

-0.47

 Signalez

-0.47

oredCriteria

-0.46

NameInMap

-0.45

 stratégique

-0.45

POSITIVE LOGITS

Fuck

0.49

BTW

0.45

btw

0.45

Really

0.43

Gonna

0.42

 Really

0.42

ponses

0.42

 Fuck

0.41

Weird

0.41

Basically

0.41

Activations Density 3.699%

references to personal experiences and inquiries

No Known Activations