INDEX

Explanations

geographic location names and references to specific states

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

AxisAlignment

-0.46

rawDesc

-0.43

featureID

-0.43

nack

-0.42

 esternos

-0.41

 indisponible

-0.41

 विश्वसनीयता

-0.40

onomic

-0.39

',

-0.38

alp

-0.38

POSITIVE LOGITS

Бележки

0.47

 Wicidata

0.45

 sentada

0.45

 NSCoder

0.43

Viited

0.43

;->

0.43

AddWithValue

0.42

 eût

0.42

@[+][

0.42

ThroughAttribute

0.42

Activations Density 0.384%

geographic location names and references to specific states

No Comments

No Known Activations