INDEX

Explanations

references to accusations or allegations of wrongdoing

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

Collusion, leaking, or conspiracy allegations

np_acts-logits-general · gemini-2.0-flash

clandestine plotting and influence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

出版年

-0.66

 aceptas

-0.56

 considérons

-0.55

 tauto

-0.54

AddAttribute

-0.52

rzej

-0.52

uarts

-0.51

⎩

-0.51

aughey

-0.51

 descriptors

-0.51

POSITIVE LOGITS

 plot

1.27

 plotting

1.20

 conspired

1.19

 conspiracy

1.17

 Plot

1.16

plot

1.16

 plots

1.12

 conspir

1.08

Plot

1.07

 collusion

1.05

Activations Density 0.777%

references to accusations or allegations of wrongdoing

Collusion, leaking, or conspiracy allegations

clandestine plotting and influence

No Comments

No Known Activations