INDEX

Explanations

references to hierarchical structures or levels within a data framework

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

MIDDLEWARE

-0.85

SDC

-0.80

 isComment

-0.77

 Chamb

-0.77

httphttps

-0.76

żeli

-0.73

 Macao

-0.71

 fibrillation

-0.71

 Disqus

-0.70

verwijspagina

-0.70

POSITIVE LOGITS

 ROOT

1.53

 Root

1.50

 Roots

1.43

 roots

1.43

 root

1.41

ROOT

1.36

roots

1.34

Roots

1.33

root

1.31

Root

1.25

Activations Density 0.069%

references to hierarchical structures or levels within a data framework

No Comments

No Known Activations