INDEX

Explanations

elements related to professional experience and roles

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

work or job experience

np_acts-logits-general · gemini-2.0-flash

past positions and employment history

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

)++;

-0.52

eload

-0.48

 apla

-0.43

Calendario

-0.43

])):

-0.43

 index

-0.42

 theirs

-0.42

Sitz

-0.42

ķ

-0.41

 scheduled

-0.41

POSITIVE LOGITS

webElementXpaths

0.84

 experience

0.72

 समीक्षाओं

0.70

DockStyle

0.70

 career

0.69

 esperienze

0.69

 experiences

0.68

letzt

0.68

 يتيمه

0.66

 nakalista

0.65

Activations Density 0.309%

elements related to professional experience and roles

work or job experience

past positions and employment history

No Comments

No Known Activations