INDEX

Explanations

references to residency status and related terminology

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

"Resident Evil" or references to residents

np_acts-logits-general · gemini-2.0-flash

Resident Evil

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

Personendaten

-0.89

elemField

-0.84

 HttpHeaders

-0.81

 AssemblyCulture

-0.77

DispatchToProps

-0.77

initComponents

-0.73

zzleHttp

-0.72

jsonwebtoken

-0.72

 '\\;'

-0.71

IUrlHelper

-0.71

POSITIVE LOGITS

 residents

0.94

 Residents

0.84

Residents

0.79

residents

0.70

 resident

0.67

 hall

0.58

Resident

0.53

=<?

0.53

resident

0.53

 miesz

0.53

Activations Density 0.133%

references to residency status and related terminology

"Resident Evil" or references to residents

Resident Evil

No Comments

No Known Activations