INDEX

Explanations

questions and inquiries about concepts and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 <=",

-0.46

SourceChecksum

-0.39

di

-0.38

pan

-0.37

 machine

-0.37

dis

-0.35

pin

-0.35

ホ

-0.35

HOS

-0.35

AdapterFactory

-0.34

POSITIVE LOGITS

EndInit

0.60

 feroit

0.55

 forstå

0.54

 enfans

0.49

 otomatig

0.49

 nonUne

0.46

twimg

0.45

phazard

0.45

AnchorTagHelper

0.45

 donnera

0.45

Activations Density 0.444%

questions and inquiries about concepts and their significance

No Comments

No Known Activations