INDEX

Explanations

words associated with locations and communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ligiloj

-0.38

SFD

-0.34

AI

-0.34

True

-0.32

 учё

-0.32

 Ihrem

-0.31

antwoorden

-0.31

 äusser

-0.31

ονται

-0.31

 croy

-0.31

POSITIVE LOGITS

 BrowserModule

0.60

enterOuterAlt

0.49

 raided

0.49

RenderAtEndOf

0.49

tagHelperRunner

0.48

setAccessible

0.48

ViewImports

0.47

WebServlet

0.47

BorderFactory

0.47

EndProject

0.46

Activations Density 1.139%

words associated with locations and communities

No Comments

No Known Activations