INDEX

Explanations

references to significant life events and health-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 Narcis

-0.62

 herring

-0.60

◄

-0.58

EndInit

-0.58

 gallbladder

-0.56

 Cooler

-0.56

աստ

-0.56

تقاوى

-0.54

BaseType

-0.53

 Noodle

-0.52

POSITIVE LOGITS

RetentionPolicy

0.54

ोग

0.47

his

0.44

 iprot

0.43

ρας

0.43

 unique

0.43

pejo

0.42

Ambos

0.42

 indisponible

0.42

gency

0.42

Activations Density 0.556%

references to significant life events and health-related topics

No Comments

No Known Activations