INDEX

Explanations

references to specific job titles and roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

IBOutlet

-0.38

 ExecuteAsync

-0.35

 IBOutlet

-0.35

 siker

-0.34

 Infórmanos

-0.34

rentiel

-0.34

ReusableCell

-0.33

__(/*!

-0.33

 inalámbrica

-0.32

nasse

-0.32

POSITIVE LOGITS

 appointed

0.63

#+#

0.58

 appointment

0.56

OGND

0.54

 liaison

0.54

appointed

0.52

 appoint

0.50

+#+#

0.50

pyx

0.50

 designated

0.49

Activations Density 0.366%

references to specific job titles and roles

No Comments

No Known Activations