INDEX

Explanations

references to espionage and intelligence activities

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

mentions of spies, intelligence agencies, undercover agents, and related espionage or national-security terms.

oai_token-act-pair · gpt-5-mini Triggered by @phamvanluong2003

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 AssemblyCulture

-0.86

RegressionTest

-0.75

esModule

-0.72

AnimationsModule

-0.72

IndentedString

-0.71

出版年

-0.61

PYX

-0.61

Vidite

-0.60

 StringTokenizer

-0.59

исленность

-0.59

POSITIVE LOGITS

 detective

1.01

 Detective

0.92

 intelligence

0.91

FBI

0.89

 detectives

0.86

 espionage

0.85

 investigative

0.85

Detective

0.83

 detection

0.83

 Intelligence

0.82

Activations Density 0.589%

references to espionage and intelligence activities

mentions of spies, intelligence agencies, undercover agents, and related espionage or national-security terms.

No Comments

No Known Activations