INDEX

Explanations

references to military context and personnel

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

interopRequire

-0.69

COUVER

-0.68

kozások

-0.59

webElementXpaths

-0.54

 LUMI

-0.53

rungsseite

-0.50

 createState

-0.50

 ویکی‌پدیا

-0.49

NewUrlParser

-0.49

MigrationBuilder

-0.48

POSITIVE LOGITS

 military

2.17

 Military

2.02

Military

1.90

 soldiers

1.88

military

1.84

 soldier

1.82

 Army

1.81

 MILITARY

1.77

 Soldiers

1.66

 army

1.63

Activations Density 0.686%

references to military context and personnel

No Comments

No Known Activations