INDEX

Explanations

references to positions of authority and roles within organizations

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

government or administration

np_acts-logits-general · gemini-2.0-flash

government & administration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ThroughAttribute

-0.78

 BoxFit

-0.58

AxisAlignment

-0.57

хран

-0.51

 onCreateView

-0.49

stdafx

-0.48

webgl

-0.46

quilibrium

-0.46

onRequest

-0.46

 khảo

-0.45

POSITIVE LOGITS

 bureaucrats

1.20

 bureaucracy

1.17

 government

1.14

 bureaucratic

1.10

 bureauc

1.10

 Government

1.03

government

1.00

 administrative

1.00

Government

0.98

 governmental

0.94

Activations Density 0.298%

references to positions of authority and roles within organizations

government or administration

government & administration

No Comments

No Known Activations