INDEX

Explanations

specific numerical identifiers or technical codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 itſelf

-1.24

 purpoſe

-1.18

 myſelf

-1.10

Efq

-1.05

 himſelf

-1.05

 Monfieur

-0.98

 Cæsar

-0.98

 Houſe

-0.98

 Majefty

-0.97

ſelves

-0.97

POSITIVE LOGITS

PageFactory

0.48

antMatchers

0.47

mo

0.47

PageRoute

0.43

 bParam

0.42

掴

0.42

 искать

0.41

mo

0.41

Activations Density 0.023%

specific numerical identifiers or technical codes

No Comments

No Known Activations