INDEX

Explanations

evidence and references related to studies or reports

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

MessageTagHelper

-0.66

EndProject

-0.52

şiv

-0.51

 TType

-0.48

المناصب

-0.48

PostInfinity

-0.42

vician

-0.42

 дописавши

-0.42

utnik

-0.42

ThroughAttribute

-0.41

POSITIVE LOGITS

 dAtA

0.46

ValueStyle

0.44

IndentedString

0.41

 propOrder

0.39

 intptr

0.36

-------------</

0.36

 expresa

0.35

曖昧さ回避

0.34

 actions

0.33

ImageContext

0.33

Activations Density 0.702%

evidence and references related to studies or reports

No Comments

No Known Activations