INDEX

Explanations

repeated structures or patterns, particularly in code or numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.48

 surla

-0.48

-0.47

led

-0.46

 desar

-0.45

 Silber

-0.44

bcryptjs

-0.44

les

-0.44

 Godfrey

-0.43

POSITIVE LOGITS

>>>

1.36

 متعلقه

1.09

 itſelf

0.99

Efq

0.88

>>>

0.87

^(@)

0.85

 Monfieur

0.84

 myſelf

0.81

 Mahomet

0.79

impanan

0.79

Activations Density 0.191%

repeated structures or patterns, particularly in code or numerical values

No Comments

No Known Activations