INDEX

Explanations

references to specific websites or organizations, particularly around health and software topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 combination

-0.34

 familiar

-0.34

Sdn

-0.33

icleta

-0.31

 most

-0.30

ことにしました

-0.29

SuspendLayout

-0.28

の姿

-0.28

ohistochemical

-0.28

POSITIVE LOGITS

exitRule

0.62

 بيها

0.62

online

0.60

 հղումներ

0.59

სქოლიო

0.58

ErrUnexpectedEOF

0.57

Notae

0.57

enumi

0.54

RegressionTest

0.54

 Tweets

0.54

Activations Density 0.381%

references to specific websites or organizations, particularly around health and software topics

No Comments

No Known Activations