INDEX

Explanations

codes or identifiers related to data entries or records

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

fjspx

-0.48

 للاسماء

-0.47

Personendaten

-0.42

↹

-0.40

inSlope

-0.39

ГЛА

-0.37

WebElementEntity

-0.36

 HFILL

-0.34

corpions

-0.33

->___

-0.33

POSITIVE LOGITS

parsedMessage

0.59

 esternos

0.46

featureID

0.45

//=

0.44

 manqué

0.44

лтемелер

0.43

værende

0.43

ंदीखरीदारी

0.42

FormTagHelper

0.42

complexContent

0.40

Activations Density 0.240%

codes or identifiers related to data entries or records

No Comments

No Known Activations