INDEX

Explanations

references to academic titles and roles, especially in the context of research or studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Normdatei

-0.52

 asset

-0.47

 Secretary

-0.43

ɕ

-0.41

 Asset

-0.40

 RequestMethod

-0.40

 Darauf

-0.39

Secretary

-0.39

ʖ

-0.38

 оригіналу

-0.38

POSITIVE LOGITS

 profit

0.74

 profitable

0.73

 Profit

0.68

Profit

0.65

 PROF

0.65

profit

0.65

Prof

0.62

 prof

0.59

 Prof

0.59

 profitably

0.57

Activations Density 0.143%

references to academic titles and roles, especially in the context of research or studies

No Comments

No Known Activations