INDEX

Explanations

relationships and events involving employment and job status

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

a job or employment

np_acts-logits-general · gemini-2.0-flash

employment or current job status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 nonatomic

-0.53

škai

-0.49

ˌ

-0.48

 géné

-0.46

endphp

-0.45

yal

-0.43

str

-0.42

ตู

-0.41

jei

-0.41

 Κυ

-0.40

POSITIVE LOGITS

 employment

1.22

 employed

1.20

employment

1.04

 joining

1.04

 Employed

1.03

employed

1.03

 Employment

0.98

 EMPLOYMENT

0.93

Joining

0.93

Employment

0.92

Activations Density 0.441%

relationships and events involving employment and job status

a job or employment

employment or current job status

No Comments

No Known Activations

relationships and events involving employment and job status

a job or employment

employment or current job status

No Comments

No Known Activations