INDEX

Explanations

references to academic or theoretical concepts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

IFrame

Link

Negative Logits

iprot

-0.37

else

-0.33

↵↵

-0.32

AreEqual

-0.32

 categoryId

-0.32

 linked

-0.31

NSMutableArray

-0.31

fn

-0.31

isEqualTo

-0.30

Eligibility

-0.30

POSITIVE LOGITS

 disposal

0.77

 disposition

0.72

 theoretical

0.69

Theory

0.69

 dispose

0.68

 secuencia

0.68

IntoConstraints

0.68

 dispos

0.68

theory

0.68

 theory

0.68

Activations Density 0.279%

references to academic or theoretical concepts

No Known Activations