INDEX

Explanations

phrases related to employment and job roles

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

worked forworked at

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 immersive

-0.42

 magically

-0.41

 choć

-0.40

 virtual

-0.40

 powerfully

-0.40

 Schell

-0.39

 popular

-0.39

 mitad

-0.38

 strongly

-0.38

 Svensson

-0.38

POSITIVE LOGITS

 Motorola

0.59

 myſelf

0.57

EndInit

0.57

AndEndTag

0.56

########.

0.56

 ſind

0.56

 DuPont

0.54

bootstrapcdn

0.54

 Lockheed

0.54

 manufact

0.53

Activations Density 0.035%

phrases related to employment and job roles

worked forworked at

No Comments

No Known Activations